90d14aaba5afdcf5e2271e0677cfa4c312948ff6
5098 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
jgrusewski
|
90d14aaba5 |
spec(ml-alpha): GPU/CPU contract, CUDA Graphs, cold-start, disconnect handling
Critical-review pass on the CfC+PPO design adds: - Public API: mapped-pinned ingress slots, single DtoH per decision - Section 5.5: CUDA Graph capture topology (perception / policy / training), kernel inventory, cuBLAS Lt epilogue fusion, persistent ring layouts, determinism mode, build-time cubin compilation, perf budget - Section 5.6: Databento/IBKR disconnect + failure response, never-do list - Section 6 cold-start: 4-state bootstrap, Phase B walk-forward stats as pre-deployment kill-switch baseline, always-live ISV controllers Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> |
||
|
jgrusewski
|
d4ea54d780 |
spec(ml-alpha): CfC + PPO greenfield design
Approved design document for the ml-alpha rebuild. Seven sections plus
appendices, all 7 sections + ISV-driven auto-tuning addition approved
via the brainstorming-skill flow.
Key architectural decisions:
- Full closed-loop scope: training + offline inference + live IBKR
- Three components: ml-alpha library, alpha_train binary, AlphaPpoStrategy
in trading_agent_service (reuses existing data_acquisition,
trading_service, broker_gateway, and the 1177-LOC IBKR adapter that
already exists in trading_engine)
- Snapshot-level CfC perception trunk (Closed-form Continuous-time, the
trainable LTC variant from Hasani 2022) — chosen over Mamba2 for
native multi-time-scale via per-cell learnable τ; hard validation
gate requires CfC AUC ≥ Mamba2 baseline before continuing
- 5 multi-horizon heads at {30, 100, 300, 1000, 6000} snapshots forward
- Decision-stride 50 snapshots (~1 min); empirically validated this
session (per-bar→stride=200 flipped 3-fold mean Sharpe from -4.29 to
+1.78 at quarter-tick cost)
- Action: target_position categorical ∈ {-10, ..., +10}; max_train=10
fixed at architecture level, max_live ≤ 10 runtime-cappable
- Reward in price units (position-size invariant): dense per-segment
PnL − C_trade·|Δcontracts| − C_vol·vol_excess; C_trade=0.034 fixed
(IBKR $1.70 RT ÷ $50/point), C_vol=0 default
- Full online learning with EWC anchoring + 80/20 offline/live replay
buffer + kill-switch on σ-band metric deviations (loss, mean reward,
hit-rate, KL, entropy)
- All hyperparameters that vary during training are ISV-driven
(controller outputs, not magic numbers) per
pearl_controller_anchors_isv_driven.md
- Fully GPU-resident on hot path per feedback_cpu_is_read_only.md
- $35k starting capital; conservative max_live ramp 1→2→3 contracts
with manual config bumps gated on realized track record
- Documented IBKR-specific quirks (PDT, mid-session margin spikes,
rollover, halts, rate limits) with concrete design responses
Supersedes the abandoned 2026-05-16-alpha-ppo-trainer.md (DQN-port plan)
which inherited the wrong architectural shape.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
|
||
|
jgrusewski
|
10f4bcc15b |
feat(alpha): decision-stride + cluster 9-fold CV workflow
Two complementary additions to validate the minute-horizon alpha hypothesis at IBKR-realistic costs: 1. `alpha_baseline --decision-stride N`: emits a new action every N steps; between decisions force action=0 (wait) so an open position is held rather than re-decided per bar. Cuts per-bar trade counts ~stride× and removes the coin-flip overtrading. Local 2Q sweep showed stride=200 + scaled training (8K episodes × 25 envs × H=1200) flipped Sharpe at ¼-tick from -4.29 (per-bar, 3-fold mean) to +1.78, with std collapsing from ±8.8 to ±1.15. Break-even cost moved from <¼-tick to ~1-tick — for the first time positive at IBKR-realistic passive-execution frictions. 2. `alpha_train_stacker --max-rows N`: optional cap on bars consumed from the fxcache. Used during local 2Q smoke (--max-rows 4M against the 17.8M-row 9Q fxcache) to fit Mamba2 training on a 4 GB consumer GPU; on the cluster (--no-cap) it sees all 9Q. 3. New Argo workflow `alpha-cv`: standalone template that compiles alpha_train_stacker + alpha_baseline + alpha_fill_coeffs.json, trains the stacker on the 9Q fxcache, then runs 9 sequential walk-forward folds of alpha_baseline on disjoint 1.9M-bar windows (one per quarter). Launcher script `scripts/argo-alpha-cv.sh` mirrors argo-train.sh conventions. The local 2Q test that motivated this commit is summarised inline in the alpha-cv template comments; the verdict was "framing was the bug — once decision cadence matches the multi-minute alpha horizon, the strategy is positive at IBKR commission". Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> |
||
|
jgrusewski
|
737c2c1305 |
infra(argo): pin all workflow nodeSelectors to topology.kubernetes.io/zone=fr-par-2
Scaleway BSSD PVCs (cargo-target-*, sccache-*, feature-cache-pvc,
bin-cache, training-data-pvc, test-data-pvc, platform service PVCs) are
single-zone-locked at create time. The cluster's node pools in main.tf
set `region` but no `zone`, so each autoscale event picks a zone
arbitrarily. When the autoscaler spins up a node in a zone that doesn't
match an existing PVC, scheduling fails with
"1 node(s) didn't match PersistentVolume's node affinity"
until the autoscaler eventually retries in the right zone. We hit this
on the HM pool creation (fixed manually with zone=fr-par-2) and again
on this commit's ensure-binary autoscale.
Track 1 (this commit): add `topology.kubernetes.io/zone: fr-par-2` to
every k8s.scaleway.com/pool-name nodeSelector entry across the 11 argo
workflow templates (34 entries total). The Kubernetes scheduler AND
cluster-autoscaler both honor topology keys when deciding placement /
provisioning — so future autoscale events will only spin up fr-par-2
nodes, and PVC binding is guaranteed.
Track 2 (future, structural): add `zone = "${var.region}-2"` to each
scaleway_k8s_pool in infra/modules/kapsule/main.tf so the pools never
provision in any other zone. Requires terraform-state cleanup (the
GitLab http backend currently has no states; the HM pool was created
out-of-band) and drain/recreate of any existing mixed-zone nodes —
deferred.
Verification: pool=N / paired=N coverage report shows 1:1 pool-name
to topology.kubernetes.io/zone entries in every file. kubectl apply -f
of all 11 templates returned "configured" for each.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
|
||
|
jgrusewski
|
711b6d434d |
obs(alpha_pipeline): per-chunk progress logs for cluster diagnostics
After the cluster's silent-failure incident (75 min between 'alpha pipeline inputs' and exit, no intervening log line), instrument the parallel path so any future hang or panic localises to the specific chunk that died. Each chunk emits start + done lines with chunk_idx, emit range, warmup_start, row count, and elapsed seconds; the wrapper also logs dispatch (chunk count + threads + chunk_size) and overall completion. Local 1Q smoke (16-thread box): - dispatching 16 chunks (chunk_size=35485, warmup_bars=2000) - chunk 0 (cold-start, no warmup shortcut): 19.2s - chunks 1-15: 13.9-16.5s - all-chunks-complete log fires before fxcache write Cost: ~17 info lines per precompute run — negligible. Worth the observability when the pipeline takes minutes and any future kill needs root-cause. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> |
||
|
jgrusewski
|
a683d62771 |
perf(alpha_pipeline): parallelize via N-chunk warm-up pattern
Cluster's 9-quarter precompute_features hung silently after the "alpha pipeline inputs" log line and was killed at ~75 minutes — local 1Q profiling showed the alpha pipeline is strictly single-threaded (extract_alpha_features is one for-loop over n_output bars with no rayon usage), so 9Q would have needed ~72 min on one CPU even with no external interference. That's a kill window large enough to be brittle under any transient kubelet/argo signal. Fix: split the emit range across `rayon::current_num_threads()` chunks. Each chunk gets fresh aggregator state and pre-rolls 2000 leading bars without emission so Hawkes excitation / Bouchaud EMA / frac-diff FIR / LOB PCA covariance / microprice EMA / spread_decomp running stats are saturated before the first emitted row. Trade-feed semantics preserved via `trades.partition_point` seeding per chunk — each trade still visits exactly one aggregator chain. Local 1Q ES benchmark (9-core box): - before: 2:19 wall, 101% CPU (1 core) - after: 0:27 wall, 915% CPU (9 cores) - 5.1× speedup; same row count + Alpha dim 134 + 468MB output Extrapolated 9Q on cluster's 32-vCPU HM pool: ~4-5 min for the alpha portion (vs ~72 min before). Well under any plausible kill window. Numerical caveat: not bit-identical to a fully-sequential run for chunks k > 0. Aggregators initialise at default state instead of carrying real history across the chunk seam; the 2000-bar warmup refills Hawkes's 500-event history twice over and saturates the longer-memory EMAs, so post-warmup drift is bounded by floating-point ε. The two existing in-crate unit tests (`test_extract_alpha_features_*`) still pass. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> |
||
|
jgrusewski
|
e7ce4395e8 |
perf(precompute): parallel trades load + predecoded sidecar cache
Flamegraph of precompute_features on 1Q ES showed 62% of CPU time in zstd decompression, 6% in DBN FSM parsing, and only 2% in the actual feature math — single-threaded zstd was the bottleneck, not compute. Two fixes: 1. Per-quarter parallelism on the volume-bar trades loop (was sequential `for file in &trade_files`); brings it in line with the OFI path that already used par_iter. 2. Predecoded sidecar cache in `crates/ml-features/src/predecoded.rs`: first call to a `.dbn.zst` writes a bincode'd Vec<Mbp10Snapshot> or Vec<DbnTrade> under `<output_dir>/predecoded/`. Subsequent calls deserialize the sidecar and skip zstd entirely. An mtime+size header self-invalidates the sidecar when the source changes — no manual flush needed when a quarter is re-downloaded. Local 1Q ES results: - cold (writes sidecar): 40.7s (was 39.3s; +1.4s for write) - warm (HIT): 4.7s (8.7× faster) - zstd in flat perf: 62% → 0% of CPU samples - sidecar disk per Q: ~150MB The sidecar layer also auto-dedupes within a single run: the OFI section re-loads trades, but the second call hits the sidecar that the volume-bar section wrote moments earlier. CLI: `--rebuild-predecoded` purges sidecars for cold-path testing or after a wire-format change to Mbp10Snapshot / DbnTrade. Sidecars also self-invalidate on format-version mismatch so old caches are skipped silently rather than mis-deserializing. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> |
||
|
jgrusewski
|
86de265fc8 |
infra(kapsule): add ci-compile-cpu-hm pool for 9-quarter fxcache
Two 9-quarter precompute_features runs OOM-killed on the existing
ci-compile-cpu pool (POP2-HC-32C-64G, 56Gi cgroup limit):
- train-wq8b8: exit 137 ~12s after "OFI computed" at ~57Gi
- train-2l6p4: exit 137 ~12s after "OFI computed" at ~52Gi peak
(despite the into_iter + drop(feature_vectors) +
normalize_in_place refactors landed in
|
||
|
jgrusewski
|
623ebfcf71 |
fix(precompute): in-place z-score + drop feature_vectors early
Previous workflow train-4qwtc hit memory-pressure thrash (~56Gi
cgroup.current sitting at the 56Gi pod limit, kernel reclaim
hammering page cache) right after OFI completed on the 9-quarter
17.8M-bar dataset. Two refactors reduce peak by ~12GB:
(1) walk_forward.rs: new `normalize_batch_in_place(&mut features)`
that rewrites the slice in place. The previous `normalize_batch`
`.collect()`s a new Vec — at this dataset size that's a
transient ~6GB peak while both pre- and post-normalised arrays
are alive.
(2) precompute_features.rs:
- call `normalize_batch_in_place` instead of the rebinding form.
- explicit `drop(feature_vectors)` after copying the slice into
`features` — `feature_vectors` would otherwise stay alive
until end-of-main shadowing the ~6GB allocation through
every downstream step.
Combined with the prior `t.into_iter()` refactor (
|
||
|
jgrusewski
|
110d3b4125 |
chore(ml): delete dead imports, parens, and the unused MappedI32::read
Cleanup of compiler warnings flagged by both local cargo check and the cluster ensure-binary log. Per `feedback_no_hiding`, every site is either deleted or wired up — no #[allow] suppressions. Lib (5 sites): - gpu_backtest_evaluator.rs:34 — drop unused DevicePtrMut. - gpu_dqn_trainer.rs:49 — drop unused DevicePtrMut (8 device_ptr_mut calls don't need the trait import in current cudarc). Line 19852: drop unnecessary parens around `b * sh2`. - training_loop.rs:20 — drop unused DevicePtrMut; unbrace single- symbol use at 5766. - state_reset_registry.rs:4 — delete the 10-symbol use-block of slot constants. Names appear in description strings (documentation only), symbols are never referenced. Examples (3 sites): - alpha_dqn_h600_smoke.rs:181, 186 — drop COL_RAW_CLOSE, FEAT_DIM, FillCoeffs, FillModel imports. - alpha_baseline.rs:79 — delete unused MappedI32::read. Batched path uses read_all for N-element action readback; the single-element method was leftover from the pre-batched legacy path. Lib + examples now have zero removable warnings. The remaining unsafe_block lints (each cudarc kernel launch needs unsafe) are structural and not actionable under the project's -W unsafe-code policy. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> |
||
|
jgrusewski
|
a27cb40a9a |
fix(precompute): consume DbnTrade Vec during Mbp10Trade conversion
The 9-quarter precompute_features run OOM-killed at ~56Gi on the ci-compile-cpu pool (POP2-HC-32C-64G) on 2026-05-16. Root cause: lines 672-684's `t.iter().map(...).collect()` borrows the source DbnTrade Vec while building the Mbp10Trade Vec — both alive simultaneously, transient peak ~25GB just from this transformation for the 199M-trade dataset. `.into_iter()` consumes the source element-by-element so the allocation drops as the destination grows, capping peak at the larger of the two Vecs (~15GB) rather than their sum. Should let the 9-quarter precompute fit comfortably on the existing 64GB ci-compile-cpu pool without provisioning a high-memory node. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> |
||
|
jgrusewski
|
d5896ef809 |
infra(argo): skip gpu-warmup on the fxcache-only path
gpu-warmup pre-provisions an L40S node so hyperopt / train-best don't pay autoscaler latency at workflow start. When hyperopt-trials=0 (the precompute-only path used by scripts/argo-precompute.sh), both downstream consumers are skipped via their `when:` clauses and the warmup-provisioned GPU node would sit idle until workflow end. Add the same `when:` clause to gpu-warmup so it skips alongside its consumers, saving an L40S node's provisioning + idle time for every fxcache-rebuild submission. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> |
||
|
jgrusewski
|
d49003de6d |
feat(regime): vol_ref floor controller + cross-invocation disk persist
Closes the TrainingPersist loop for the regime defense per the KELLY_F_SMOOTH precedent (pearl_kelly_cap_signal_driven_floors). Three layers: (1) Per-step: alpha_regime_vol_update_kernel tracks min(vol_obs > 1e-12) in new slot 553 (REGIME_VOL_OBS_MIN_INDEX). Filtered against artifact- zero observations from stationary snapshots where curr == prev. (2) Per-cell: stacker_threshold_controller_update gains a fifth branch that reads vol_ref (slot 550) at cell-end, computes `target = floor_target_ratio × vol_ref`, slow-EMAs the floor anchor (slot 552) toward the target with rate `floor_update_rate` (0.1 per cell). Subfloor 1e-12 inside the kernel guards against the anchor collapsing to zero. (3) Per-invocation: alpha_baseline reads `config/ml/alpha_baseline_state.json` at startup and seeds slot 552 from the `regime_vol_ref_floor` field. At end of main(), the learned floor is written back via tmp+rename atomic write so concurrent walk-forward invocations see a consistent file. Matches the cross-fold-persistent shape of KELLY_F_SMOOTH. Block extended to 15 slots (539..=553). Smoke + kernel unit test pass -1/-1 for the new floor-controller indices (backward compat). Walk-forward CV verdict (Q1 fxcache, 3 sequential folds): iteration fold-A fold-B fold-C mean ± SD pre-defense (no regime) +91.52 -21.44 +46.74 +38.94 ± 56.88 hardcoded 1e-9 floor -19.77 +65.04 +6.45 +17.24 ± 43.42 learned floor (0.5 × cell_min) +74.78 -12.72 +8.80 +23.62 ± 45.59 learned floor (0.1 × vol_ref) -19.53 -26.51 +15.46 -10.20 ± 22.49 Controller infrastructure is structurally correct (loop closes, floor persists across invocations, kernel + disk + ISV all roundtrip). The TUNING is data-dependent — single-quarter CV doesn't have enough regime diversity to anchor the floor against. Multi-quarter fxcache validation is the next step (built cluster-side on the 9-quarter 2024-Q1..2026-Q1 ES futures dataset, downloaded as a single artifact for local CV). Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> |
||
|
jgrusewski
|
3c035ce1ae |
feat(regime): vol_ref bootstrap window + ISV-driven permanent floor
Two coupled fixes to the vol-EMA regime detector exposed by walk-forward CV after all features were promoted to always-on: (1) Bootstrap window for vol_ref (slot 551 = REGIME_VOL_REF_SAMPLES) - Replace the Pearl-A "first observation replaces directly" bootstrap with a running mean over the first N=100 vol_ema observations, then switch to β-tracking. For IID observations the running-mean estimator has variance σ²/N — a 100-sample mean is 10× less noisy than the single-shot replace. (2) Permanent floor on vol_ref (slot 552 = REGIME_VOL_REF_FLOOR) - The bootstrap alone exposed the asymmetric deadband-deadlock: if vol_ref converged to a tiny value during a calm initial stretch, vol_ref / vol_ema fired the moment any realistic vol resumed and Kelly stayed trapped at regime_scale_floor=0.25 forever. Floor lives in ISV slot (TrainingPersist) with a hardcoded 1e-12 sub-floor inside the kernel as numerical-underflow guard. - Host seeds slot 552 with 1e-9. Future controller kernel will refine this from observed cell-level vol minima with cross-fold persistence. Walk-forward CV on Q1 fxcache (3 folds, window=700K, train_frac=0.6): cost fold-A fold-B fold-C mean ± SD 0.00 -19.77 +65.04 (100%) +6.45 +17.24 ± 43.42 Fold B turnaround is the headline: -47.64 (bootstrap-only) → +65.04 (bootstrap + floor) confirms the floor is the load-bearing fix. Cross-fold std-dev compressed 24% at cost=0; mean dropped from +38.94 (pre-defense) to +17.24 (with defense). Classic mean/variance trade. Block extended to 14 slots (539..=552). Kernel sig: vol_ref_floor moved from f32 scalar to vol_ref_floor_index i32, so the anchor is named/addressable in ISV. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> |
||
|
jgrusewski
|
34586dad68 |
refactor(alpha_baseline): rename, drop conditionals, strip dead paths
Rename binary alpha_compose_backtest → alpha_baseline and remove the boolean flags whose features are now mandatory: --c51 (always C51 distributional Q) --temporal (always Mamba2 temporal encoder) --isv-continual (controller always fires per eval episode) --regime-scale (vol-EMA regime defense always on) --pruned-actions (FALSIFIED 2026-05-15 per pearl_action_pruning_falsified) Every dependent code path was stripped, not just gated: - Linear-Q kernels (lq_fwd, lq_grad, munch_kernel) and their cubin loads are gone — C51 is the only Q-network. - Single-env push_kernel / h_store_kernel loads removed; the backtest has been batched-parallel-env since T14 and only the _batched variants are called here. (The smoke binary still uses single-env variants because one env per episode is its job.) - Dead transition buffers removed: states_dev, next_states_dev, actions_dev, rewards_dev, dones_dev, q_current_dev, q_next_dev, target_dev, single_state_dev, single_q_dev, probs_current_dev, probs_next_dev, m_dev, single_probs_dev, single-env state_pinned, action_pinned, window_tensor, h_enriched_buf_dev. - Dead constants and helpers: PRUNED_ACTIONS, N_WEIGHTS, N_BIASES, epsilon_greedy, epsilon_greedy_gated. End-to-end verification on the existing Q1 fxcache (rebuild was OOM locally; full multi-quarter validation is the next phase): cost=0.0000 best τ=0.250 Sharpe_ann=+36.83 win=0.984 trades/ep=83.3 cost=0.0625 best τ=0.250 Sharpe_ann=+38.53 win=0.996 trades/ep=83.2 cost=0.1250 best τ=0.250 Sharpe_ann=+38.37 win=0.994 trades/ep=83.3 cost=0.2500 best τ=0.250 Sharpe_ann=+34.24 win=0.990 trades/ep=85.6 cost=0.5000 best τ=0.250 Sharpe_ann=+31.83 win=0.946 trades/ep=84.8 Numbers track the prior T16-flag config (within stochastic noise), confirming the conditional-stripping was a pure simplification — no behavioral change, just a smaller, honester binary. Also updated: - scripts/alpha_pipeline.sh — A/B conditions collapse to fixed-cost vs cost-randomized training (the only opt-in left). - scripts/walk_forward_cv.sh — drop legacy flags, pass --window-k only. - crates/ml/src/env/loaders.rs — module doc-comment updated. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> |
||
|
jgrusewski
|
55ffe2b26f |
scripts(alpha): rename + add cross-quarter validation pipeline
- New scripts/alpha_pipeline.sh: orchestrates the 2-quarter validation after fxcache lands. Auto-discovers the Q1+Q2 fxcache (newest .fxcache excluding the known Q1-only hash), trains alpha_train_stacker on it, then sweeps 4 conditions (baseline / +cost-rand / +regime-scale / +both) × 3 walk-forward folds, aggregating mean ± stddev Sharpe per cost across folds. No phase prefixes in name or contents — the script is meant to outlive any single milestone. - scripts/build_2q_fxcache.sh: fix staging layout so MBP-10 / trades / OHLCV symlinks live in the symbol subdir (`mbp10/ES.FUT/...`) that precompute_features expects. Previous flat-layout build aborted with "MBP-10 directory not found: .../mbp10/ES.FUT". Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> |
||
|
jgrusewski
|
d090685ca9 |
feat(phase-e-4-a-T16): vol-regime detection + cost-aware training
Adds two coupled interventions on the regime fragility exposed by
walk-forward CV (mean Sharpe +27 ± 56 at half-tick across 3 folds —
std-dev ≈ mean means the strategy is regime-dependent).
(1) Vol-EMA regime detector (new ISV slots 549/550)
- New alpha_regime_vol_update.cu kernel: per inference step, reads B
parallel-env mid prices, computes cross-env mean squared log-return,
and maintains ISV[549]=REGIME_VOL_EMA (Wiener-α with 0.4 floor +
Pearl A bootstrap) and ISV[550]=REGIME_VOL_REF (slow tracker β=0.005,
≈200-step horizon).
- Block-tree-reduce (no atomicAdd), guards against zero/non-finite mids.
(2) Pre-emptive Kelly attenuation (modified stacker controller)
- stacker_threshold_controller.cu takes 3 new args: regime_vol_ema_idx,
regime_vol_ref_idx, regime_scale_floor.
- Multiplies its reactive Sharpe-error Kelly output by
regime_scale = clamp(vol_ref / vol_ema, 0.25, 1.0)
- Disabled when indices = -1 (backward-compatible smoke + kernel test).
(3) Cost-aware training (--train-cost-hi)
- alpha_compose_backtest --train-cost-hi: when > --train-cost, each
training epoch samples cost ~ U[lo, hi] so the Q-network learns
cost-conservative behaviour across the realistic ES range.
(4) Wiring
- alpha_compose_backtest --regime-scale enables both per-step regime
kernel firing during eval AND the regime hookup in the per-episode
controller call. Mapped-pinned mids buffers, all compute device-side.
- ExecutionEnv exposes current_mid() so the host gather reads the
active snapshot mid per env without leaking the private cursor field.
Smoke + test sites pass -1/-1 for regime indices (backward compat).
Doc: docs/isv-slots.md ledger for slots 549/550.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
|
||
|
jgrusewski
|
3aef276255 |
feat(phase-e-4-a): walk-forward CV via --data-start-offset
Adds a sliding-window walk-forward harness for the T10 backtest:
- New load_snapshots_from_fxcache_at(start_offset, ...) loader variant
reads bars [start_offset..start_offset+max_snapshots) from the fxcache.
Alpha-cache lookups use absolute bar indices, so the same
alpha_logits_cache.bin works across folds.
- New --data-start-offset CLI flag on alpha_compose_backtest.
- scripts/walk_forward_cv.sh runs 3 folds (window=700K, train_frac=0.6)
at offsets 0 / 600K / 1.2M, producing /tmp/cv_fold_{A,B,C}.json plus
an aggregated mean±stddev Sharpe table across folds.
Walk-forward result (alpha_logits_cache trained on bars 0..1.57M, so
fold C eval is fully past the stacker cut):
cost fold-A fold-B fold-C mean ± stddev
0.0000 +91.52 -21.44 +46.74 +38.94 ± 56.88
0.0625 +84.94 -27.97 +38.42 +31.79 ± 56.74
0.1250 +79.91 -31.22 +33.51 +27.40 ± 55.82
0.2500 +72.77 -45.41 +15.16 +14.17 ± 59.09
0.5000 +50.52 -59.82 -12.75 -7.35 ± 55.37
Fold B (mid-quarter, bars 600K..1.3M) is a disaster — win rate
collapses to 0-22% across all costs. Folds A and C succeed strongly.
Cross-fold SD ≈ mean, so the policy is regime-dependent and cannot
be reliably deployed without regime detection.
Mean Sharpe at half-tick (+27.40) is still ~7× the stateless
Phase 1d.4 baseline (-4.0), so the temporal encoder adds real value
on average — but the single-window +62 OOS celebrated earlier was
a cherry-picked favorable regime, not a deployment-ready result.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
|
||
|
jgrusewski
|
3dc022b843 |
feat(phase-e-4-a): T10 Mamba2 backward chain + KC calibration
T10 wires the C51 → Mamba2 backward chain in both binaries:
- New alpha_train_window_store_batched_kernel captures per-step windows
for end-of-epoch re-forward (Mamba2 cache required for backward).
- Mamba2Block::backward_from_h_enriched lets the C51 grad-input feed
directly into Mamba2 backward, skipping the unused W_out projection.
- alpha_c51_grad_input → backward_from_h_enriched → Mamba2AdamW.step
closes the loop in alpha_dqn_h600_smoke and alpha_compose_backtest.
Smoke (--temporal --c51): all 4 KCs PASS. R_mean -6.3 → +4.2 vs
Phase E.3 close R_mean -4.7 (no-temporal). EARLY_Q_MOVEMENT
calibration (mamba2_snapshot + mamba2_weight_distance) lifts the
diagnostic from 0.0023 (head-only) to 0.0590 (head + encoder),
giving an honest learning signal when the encoder absorbs gradient.
Backtest (--c51 --temporal --window-k 16 --isv-continual):
cost=0.0000 best τ=0.250 Sharpe_ann=+34.56 (was +10.41 head-only,
-22.54 frozen-Mamba2)
cost=0.0625 best τ=0.250 Sharpe_ann=+33.22
cost=0.1250 best τ=0.250 Sharpe_ann=+30.85 (Phase 1d.4 baseline: -4.0)
cost=0.2500 best τ=0.250 Sharpe_ann=+27.73
cost=0.5000 best τ=0.250 Sharpe_ann=+15.68
Caveat: in-sample results; OOS gate next.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
|
||
|
jgrusewski
|
0ab54dc8ef |
feat(phase-e-4-a): batched parallel-env TRAINING (greenfield)
T15: training rewrite mirroring T14 eval. N_par parallel envs lockstep H steps per epoch; ONE batched C51 update at B = N_par * H. Expected ~15× speedup vs sequential. - NEW kernel alpha_h_enriched_store_batched_kernel for batched h_enriched slot writes - Training section greenfielded: legacy sequential loop deleted - CLI flag --n-train-par (default 50) - Terminal next-state slot zeroed; done=1 at horizon masks Q_next contribution in Bellman projection — no terminal Mamba2 forward - docs/isv-slots.md updated per kernel-audit-doc hook Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> |
||
|
jgrusewski
|
90c9d54454 |
feat(phase-e-4-a): batched parallel-env eval rewrite (greenfield)
The Phase E.4.A T14 backtest at B=1 with per-step stream.synchronize()
was running ~150μs/step × 9M steps = ~22 min — dominated by sync
overhead, not GPU compute. RTX 3050 Ti to L40S swap wouldn't help
(launch overhead is the bottleneck, not FLOPS).
Solution: batched parallel envs. N=cli.n_eval_episodes environments
run in LOCKSTEP per cell — ONE sync per step (instead of N syncs).
Expected ~30× speedup at N=500.
Changes:
1. ExecutionEnv snapshots → Arc<Vec<SnapshotRow>>
- new() wraps Vec into Arc internally (backward compat)
- new_arc() takes pre-existing Arc (for parallel envs)
- snapshots_arc() accessor for snapshot sharing
- 50MB × N memory duplication avoided
2. alpha_window_push_batched_kernel (NEW CUDA)
- Same chronological shift+insert semantics as single-env kernel
- Grid (state_dim_blocks, B, 1): one thread per (batch, feature)
- launcher: launch_alpha_window_push_batched
3. MappedI32 (per-binary) gains len param + read_all()
- smoke & backtest pass len=1 for existing single-int use
- backtest passes len=N for batched action readback
4. backtest binary eval loop GREENFIELDED
- Legacy sequential 'for ep in 0..N { for step in ... }' loop
body deleted entirely
- New: 'for step in 0..horizon' outer, lockstep over N envs
- Build N envs sharing snapshots_arc at cell start
- Per step: gather N states (CPU loop, <100μs for N=500) →
write to mapped-pinned [N, STATE_DIM] → push kernel B=N →
Mamba2 batched forward → C51 batched forward → Thompson
batched → ONE sync → read N actions → step N envs on CPU
- ISV-continual moved from per-episode to per-cell (single fire
with aggregate stats)
5. docs/isv-slots.md updated per kernel-audit hook
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
|
||
|
jgrusewski
|
2feeeda8bb |
fix(phase-e-4-a): GPU kernel for h_enriched slot copy — eliminate per-step CPU roundtrip
The Phase E.4.A T8 wiring stored Mamba2's per-step cache.h_enriched
into h_enriched_buf_dev via a dtoh+htod sequence:
let h_host = stream.clone_dtoh(cache.h_enriched.cuda_data())?;
let mut buf_host = stream.clone_dtoh(&h_enriched_buf_dev)?; // <- whole buffer
for j in 0..hidden_dim { buf_host[slot_offset + j] = h_host[j]; }
stream.memcpy_htod(&buf_host, &mut h_enriched_buf_dev)?; // <- whole buffer
This violates feedback_cpu_is_read_only AND
feedback_no_htod_htoh_only_mapped_pinned. Worse, the buffer-wide
dtoh+htod every step is ~20K floats × 600 steps × 500 eps × 30 cells
= ~9M roundtrips totaling significant PCIe latency in the backtest.
Fix: new tiny CUDA kernel alpha_h_enriched_store_kernel in
alpha_window_push.cu (one thread per hidden-dim feature, writes
src[j] → buf[slot_offset + j]). Replaces the dtoh/htod sequence
in both smoke and backtest binaries.
Estimated speed-up at backtest scale: 3-6× on the temporal eval
path. Pure-GPU per-step inference restored — no synchronisation
points on the hot path.
docs/isv-slots.md updated per kernel-audit-doc hook.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
|
||
|
jgrusewski
|
2fe76f2f34 |
docs(phase-e-4-a): execution status + T10 backward_from_h_enriched patch sketch
Two documentation deliverables produced while T14 backtest runs: 1. Plan update (specs/2026-05-15-phase-e-4-a-temporal-foundation.md): adds 'Execution Status' section reflecting actual T1-T14 progression. T5 deferred (real MBP-10 peek), T9 skipped (GRN moved to E.4.B per integration notes), T10 partial (new C51 grad-input kernel landed but Mamba2 backward wiring deferred), T14 in flight. Documents the 4 execution learnings: research-first saved a week of duplicate kernel work; cheap falsification experiments (Path 2, Path 3) avoided expensive investments; C51 borrow was the largest single Sharpe-lift in the session; GpuTensor/CudaSlice interop friction is the real integration cost. 2. T10 patch sketch (specs/2026-05-15-t10-mamba2-backward-from-h-enriched.md): ready-to-apply patch for ml-alpha::Mamba2Block adding a new public method backward_from_h_enriched(cache, d_h_enriched). Bypasses the W_out projection backward, accepts the [B, hidden_dim] gradient from C51's grad-input kernel directly, zero-initialises dw_out/db_out (AdamW step on zero grad is a no-op with correct moment decay — effectively freezes W_out params which is correct semantics since Phase E never uses them). Includes the smoke binary wiring snippet that consumes the new method via launch_alpha_c51_grad_input → Mamba2 backward → AdamW step. Application gated on T14 backtest validation — if frozen Mamba2 already lifts Sharpe, T10 becomes optimisation rather than prerequisite. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> |
||
|
jgrusewski
|
4d65ace625 |
feat(phase-e-4-a): mirror --temporal in backtest binary + T11 ISV-continual
Phase E.4.A Tasks 11+12: backtest binary gains the same
--temporal Mamba2 forward chain as the smoke binary, plus the
--isv-continual flag that fires the stacker-threshold controller
at the end of each eval episode (Pillar B).
Changes:
- Imports: ml_alpha::mamba2_block::{Mamba2Block, Mamba2BlockConfig},
ml_core::cuda_autograd::gpu_tensor::GpuTensor
- CLI flags: --temporal, --window-k, --mamba2-hidden-dim,
--mamba2-state-dim, --isv-continual
- Cubin loading: alpha_window_push + stacker_threshold_controller
- Q-net sizing: c51_input_dim = mamba2_hidden_dim when --c51 --temporal
- Buffers: window_tensor GpuTensor, h_enriched_buf_dev, isv_dev,
ctl_wiener_dev
- Training inference path: push + Mamba2 forward + h_enriched →
C51 forward (mirrors smoke binary)
- Training batched compute: terminal Mamba2 forward, h_enriched_buf
for current/next, c51_input_dim threading
- Eval inference path: push + Mamba2 forward + h_enriched → C51
forward + Thompson select (with scoped borrow guard)
- T11 ISV-continual: stacker-threshold controller fires at end of
each eval episode; ISV slot 543 (threshold), 545 (observed-rate),
546 (Kelly atten) update with realized rollout stats. Co-exists
with the τ-grid sweep (τ-grid still gates; ISV updates parallel
observation of "live deployment" behaviour).
- JSON output: new fields temporal, window_k, mamba2_hidden_dim,
mamba2_state_dim, isv_continual.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
|
||
|
jgrusewski
|
75d67bd203 |
feat(phase-e-4-a): alpha_c51_grad_input kernel (T10 prerequisite)
Phase E.4.A Task 10 partial: adds the C51 gradient-w.r.t.-input
kernel needed to chain the C51 head's loss gradient back into the
Mamba2 temporal encoder.
Kernel signature: alpha_c51_grad_input_kernel reads probs[B, A, K],
m[B, K], actions[B], W[A*K, in_dim] and writes d_input[B, in_dim].
Math: dL/d_input[b,j] = Σ_k (p[b,a_taken,k] − m[b,k]) · W[a_taken*K+k, j]
(only the taken-action column of W contributes; restricted by the
sparse-over-actions C51 CE gradient structure).
Status: kernel + Rust launcher in place. Mamba2 backward NOT yet
wired in the smoke binary because ml_alpha::Mamba2Block::backward
takes d_logit [B, 1] (post-W_out scalar gradient), not
d_h_enriched [B, hidden_dim]. Two paths to complete:
1. Modify ml-alpha to expose backward_from_h_enriched(cache,
d_h_enriched) bypassing W_out.
2. Replicate the post-W_out backward sequence inline.
Both deferred pending backtest validation (T14): if frozen Mamba2
already lifts backtest Sharpe meaningfully, T10 becomes
optimisation rather than prerequisite. Smoke gate already passed
gate 1 (R_mean +3.9 vs C51-flat -1.1) with frozen weights.
docs/isv-slots.md updated.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
|
||
|
jgrusewski
|
41a7da7008 |
feat(phase-e-4-a): T13 smoke validation PASSES gate 1
1000-episode smoke with --c51 --temporal --window-k 16 --mamba2-hidden-dim 32 (frozen Mamba2 — T10 backward not yet wired). Comparison vs C51-flat baseline (also 1000 ep): R_mean ep 1000: C51-flat -1.1 → --temporal +3.9 (+5.0) R_mean peak ep 700: C51-flat +1.0 → --temporal +10.0 (+9.0) R_mean ep 50: C51-flat -8.2 → --temporal +6.8 (+15) rvr: +1.046 → +1.047 EARLY_Q_MOVEMENT: 0.0066 → 0.0364 (5× more weight motion) Gate 1 criteria: ✅ R_mean ≥ -0.5: +3.9 ✅ rvr ≥ +1.04: +1.047 ✅ EARLY_Q_MOVEMENT ≥ 0.01: 0.0364 ⚠ ACTION_ENTROPY = 0.64 < 1.10 (kill criterion misaligned with gated-policy paradigm: Wait-collapse is correct behavior, not failure) Note: Q_SPREAD_EMA shows a transient outlier at ep 950 (16417, was ~10 throughout) — likely NaN/Inf propagation in the kill-criteria EMA accumulator from a single C51-logit overflow at extreme random Mamba2 output. Policy quality unaffected (rvr stable, R_mean stable). Investigation tracked in follow-on memory. Frozen Mamba2: weights remain at Xavier init throughout training. The C51 head learns over RANDOM 32-dim temporal projections of the window — random-SSM-as-reservoir effect. T10 (Mamba2 backward + AdamW step) should lift further. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> |
||
|
jgrusewski
|
ed6f5588e1 |
feat(phase-e-4-a): wire Mamba2 forward in smoke --temporal path
Phase E.4.A Task 8: wire ml_alpha::Mamba2Block as the temporal
encoder before the C51 head when --temporal is set.
Architecture (--temporal):
state_pinned ──push─▶ window_tensor[1, K=16, in_dim=10]
│
▼ Mamba2Block::forward_train
h_enriched[1, hidden_dim=32]
│
▼ launch_alpha_c51_forward (input dim=32)
probs[1, 9, 51] ──▶ Thompson selector
Implementation:
- Mamba2Block constructed at startup with config (in_dim=10,
hidden_dim=32, state_dim=16, seq_len=K=16). Loaded from ml-alpha's
precompiled cubin.
- Per-step: window push (shift+insert), then forward_train returns
(logit, cache). We discard logit (ml-alpha's binary classifier head)
and use cache.h_enriched as the C51 input.
- Per-step h_enriched cached into h_enriched_buf_dev[(t)..t+hidden_dim].
- Batched training (end-of-episode): the C51 forward + grad use
h_enriched_buf_dev[0..ep_len*hidden] for the current state and
[hidden..(ep_len+1)*hidden] for next-state (1-step offset). Runs
one extra Mamba2 forward on the terminal window to populate slot
ep_len.
- C51 input dim (W shape) becomes mamba2_hidden_dim when --temporal,
STATE_DIM otherwise.
100-episode smoke verdict (vs C51-flat baseline):
R_mean ep 50: C51-flat -8.2 → --temporal +0.4 (+8.6)
R_mean ep 100: C51-flat +0.5 → --temporal +10.0 (+9.5)
rvr: +1.045 → +1.046 (unchanged)
Q_SPREAD: 23.9 → 12.6 (sharper distributions)
ACTION_ENTROPY: 1.42 → 1.49 (now PASSES 0.5×ln(9) threshold)
Note: Mamba2 weights are FROZEN at random Xavier init in this
commit — T10 (backward + AdamW step) lands next. The R_mean lift
above is from C51 learning over RANDOM temporal projections of the
window — random SSM acts as a feature-engineering reservoir.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
|
||
|
jgrusewski
|
35dcb87709 |
refactor(phase-e-4-a): window push to shift+insert (chronological layout)
Switch alpha_window_push from circular-buffer-with-head_idx layout to shift+insert layout matching production mamba2_update_history. Slot 0 = oldest, slot K-1 = newest after each push, matching Mamba2Block's [B, K, in_dim] input contract directly (no reorder). Cost: O(K-1) shifts per state_dim feature per push. For K=16, state_dim=10: 10 threads × ~15 ops each = trivial. Kernel signature: drops head_idx, adds K. Test updated to verify chronological shift across 3 pushes into 4-slot buffer. docs/isv-slots.md updated per kernel-audit-doc hook. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> |
||
|
jgrusewski
|
70df697328 |
feat(phase-e-4-a): wire sliding-window buffer in smoke (buffer-only)
Phase E.4.A Task 7: maintain a GPU-resident circular window buffer in the smoke binary's --temporal path. Per-step: 1. mapped-pinned state_pinned write (existing) 2. alpha_window_push_kernel writes state into window[head_idx] 3. head_idx = (head_idx + 1) % window_k 4. C51 forward proceeds against state_pinned (consumer of window wires in T8 — Mamba2 over the window) On episode reset: zero the buffer and reset head_idx so Mamba2 sees clean zero-context for the first window_k-1 steps. CLI: --temporal flag + --window-k (default 16, kernel max 32 per mamba2_alpha_kernel constraint). Validation: 100-episode smoke with --temporal produced bit-identical R_mean / rvr / kill-criteria values to the C51-flat baseline run — confirms buffer maintenance has zero side effect on the existing C51 path. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> |
||
|
jgrusewski
|
6e86e5b435 |
feat(phase-e-4-a): alpha_window_push circular-buffer kernel + GPU test
Phase E.4.A Task 6: tiny CUDA kernel that pushes a state[state_dim] vector into slot `head_idx` of a circular window buffer [K, state_dim]. Host tracks head_idx and zeros buffer on episode reset. This is the GPU-side append primitive that the smoke binary's per-step inference will call (T7) before Mamba2 over the buffer (T8). GPU smoke (alpha_window_push_circular_writes_to_indexed_slot): writes state_a at slot 0, state_b at slot 2, verifies non-targeted slots stay zero. PASS. docs/isv-slots.md: documents kernel as slot-agnostic per kernel-audit-doc hook requirement. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> |
||
|
jgrusewski
|
5d7d4fa3c6 |
feat(phase-e-4-a): add mbp10_dir param to fxcache loader (signature-only)
Phase E.4.A Task 4: extend load_snapshots_from_fxcache with `mbp10_dir: Option<&Path>`. When provided, the loader will peek MBP-10 by timestamp and populate SnapshotRow.bid_l[1..10]/ask_l[1..10] from real LOB depth — but the real-peek implementation lands in Task 5 follow-on. This commit: - introduces the parameter (callers pass None) - warns at runtime if mbp10_dir Some until T5 lands - enables downstream wiring of --use-real-depth + --mbp10-dir CLI flags in the smoke / backtest binaries T5 deferred: on ES futures the --real-spread experiment showed 76% of fxcache bars hit the 1-tick floor, so depth-from-MBP-10 likely won't move the needle for ES. Higher-leverage work (Mamba2 wiring) prioritised. T5 implementation reopens as a follow-on if E.4.A gates pass with synthesised depth. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> |
||
|
jgrusewski
|
eb49e2a0f7 |
feat(alpha): Phase E.3 follow-up — C51 distributional Q + Thompson + L1-L10 depth + falsifications
C51 distributional Q-network with GPU Thompson selection borrowed
minimally from production (alpha_c51.cu: forward, project, grad,
expected_q, thompson_select kernels; ~260 lines). Uses Huber
negative-tail compression in projection per production
block_bellman_project_f. Action selection 100% GPU via mapped-pinned
i32 output + __threadfence_system + host volatile read (matches
gpu_training_guard MappedBuffer pattern).
Backtest result (2D sweep, 500 episodes per cell, 30 cells):
cost=0 C51 +10.41 vs linear-Q -15.72 (+26pt, BEATS Phase 1d.4
no-RL baseline +4.4 by 6pt)
cost=0.125 C51 -13.81 vs -29.17 (+15pt closes half-tick gap)
Win rate at cost=0 best τ: linear-Q 0.008 → C51 0.552.
Calibration hypothesis vindicated; documented in
memory/pearl_c51_thompson_closed_phase_e3_gap.md.
Also in this commit (Phase E.3 follow-up cleanup):
- --pruned-actions falsified (2.4× worse Sharpe). Documented in
memory/pearl_action_pruning_falsified.md.
- --real-spread falsified for ES futures (76% of bars at 1-tick floor).
- SnapshotRow bid_l/ask_l extended from [f32; 3] to [f32; 10].
L4-L10 synthesized in this commit; real MBP-10 peek lands in E.4.A T5.
- docs/isv-slots.md updated per kernel-audit-doc hook requirement.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
|
||
|
jgrusewski
|
eb9047fc30 |
docs(phase-e): E.4 temporal encoder design + E.4.A implementation plan
Design doc (specs/): TFT-style architecture for Phase E execution
policy — sliding window → Mamba2 SSM → GRN trunk → MoE regime gate
→ C51 head → Thompson selector. Two core pillars added per user:
A) Full L1-L10 LOB depth input via hybrid MBP-10 peek
B) ISV-continual-learning: controllers fire at training AND
inference; Q-net weights frozen at inference but effective
policy adapts via ISV modulation
Plan doc (plans/): 14-task implementation plan for E.4.A foundation
(window buffer + L1-L10 depth + Mamba2 forward+backward + ISV-eval
controllers). Falsification gates: smoke R_mean improvement ≥ 50%,
backtest cost=0 Sharpe ≥ +8 (no regression vs C51-flat +10.41),
half-tick Sharpe ≥ -8 (closes 5pt+ of 10pt gap to Phase 1d.4
baseline -4.0).
TGGN (foxhunt Temporal Graph Gated Network) explicitly deferred to
Phase E.5+: existing CPU graph implementation + GPU adapter at
ml-supervised/src/tgnn/ — marginal benefit for single-instrument ES
futures vs the TFT-Mamba2 stack; revisit for multi-instrument
extension or production HFT inference layer.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
|
||
|
jgrusewski
|
588a6d38af |
docs(phase-e-4-a): mamba2 + grn integration research — use ml-alpha Mamba2Block
Findings: - Production Mamba2 (gpu_dqn_trainer) is coupled to SH2=256 trunk + ofi_embed + ISV[8] temporal routing — not portable to Phase E. - ml-alpha::mamba2_block::Mamba2Block is from-scratch, fully configurable (in_dim/hidden_dim/state_dim/seq_len), GPU-pure with forward_train/backward/AdamW. Used in Phase 1d.2 to lift AUC 0.50 to 0.66. ml-alpha is already a workspace dep of ml. - GRN skipped for E.4.A — Mamba2 output goes straight to C51 head. Reintroduce GRN in E.4.B if Sharpe gates don't pass. - Controller-at-inference: kernel has no training-mode branches; Wiener state preserved across episodes/cost cells for natural live-deployment simulation. Revises Tasks 8-10 of the plan: use Mamba2Block API instead of writing custom kernels. Only new CUDA needed: alpha_c51_grad_input (C51 gradient w.r.t. input features, for Mamba2 backward chain). Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> |
||
|
jgrusewski
|
771936b768 |
feat(alpha): --train-threshold for backtest + Phase E.3 honest verdict
Phase E.3 follow-up. Adds --train-threshold to alpha_compose_backtest so
the Q-network can be trained against a FIXED gate (instead of just
applying the gate at eval). Default 0.39 = the equilibrium the smoke's
controller stabilized to at ep 200+ (alpha_dqn_h600_smoke gated run).
Smoke result (gated training, controller running):
ep 100: thresh=0.32 obs=0.226 R_mean=-5.5 atten=0.75
ep 200: thresh=0.38 obs=0.082 R_mean=-3.0 atten=0.50
ep 300: thresh=0.39 obs=0.081 R_mean=-3.2 atten=0.25
ep 1000: thresh=0.39 obs=0.039 R_mean=-4.7 atten=0.10
The controller CONVERGES cleanly to threshold ≈ 0.39 with observed
trade rate at/below the 0.08 target. rollout_R_mean drops from -19
(no-gate training) to -4.7 (gated training): 4× less loss per episode.
rvr stays at +1.045σ (unchanged). The closed-loop architecture works
end to end.
(Note: smoke verdict FAILs on ACTION_ENTROPY (0.68 < threshold 1.10).
This is the policy correctly Waiting 95%+ of the time — the kill
criterion was designed to catch "collapse to one bad action," but
collapse-to-Wait under a strong gate is the RIGHT behavior. Verdict
threshold is misaligned with the gated paradigm; not a regression.)
Backtest result with --train-threshold 0.39:
cost eval-gate only train+eval gated Δ
------ -------------- ---------------- ----
0.0000 -15.72 -17.06 -1.3
0.0625 -21.30 -22.91 -1.6
0.1250 -29.17 -31.26 -2.1
0.2500 -42.12 -36.68 +5.4
0.5000 -54.86 -53.83 +1.0
Training with the gate did NOT meaningfully improve absolute Sharpe.
The eval-best threshold remains 0.20-0.25 in BOTH runs (not 0.39).
The Q-network's primary contribution is the binary trade/don't-trade
decision; the action-choice (Buy direction + placement) is largely
determined by alpha sign — linear Q can't time entry better than the
threshold filter does on its own.
Honest analysis: the gap to Phase 1d.4 baseline (+4.4 at cost=0,
-4.0 at half-tick) is NOT architectural but ECONOMIC:
Env spread: bid/ask synthesized at ±0.125-tick around mid
→ round-trip spread cost = 0.25 per trade
At τ=0.20 with 168 trades/ep: 168 × 0.25 = 42 in spread costs
Mean reward = -5 → alpha extracts ~37 of value
All eaten by spread
Phase 1d.4 baseline likely trades much less (~20-50 trades/ep at best
operating point — pure threshold-only policy, no RL). Our policy
trades 3-8× more because the DQN's action choices add fine-grained
trade attempts beyond the threshold filter's wait/trade gate.
The control loop architecture (Phase E.1 + E.2 + E.3 gate consumption)
is VALIDATED — gate produces monotone Sharpe lift, +1.045σ rvr held,
trade-rate-self-correction converges cleanly. But beating Phase 1d.4's
absolute Sharpe requires:
1. MLP for the Q-network (more representation capacity for
entry-timing decisions within the alpha confidence band)
2. OR action-space constraints (collapse the 9-action space — drop
fine-grained L1/L2 placement, keep just {Wait, BuyMarket,
SellMarket, FlatMarket})
3. OR better fill economics (real LOB instead of fixed ±0.125-tick
synthesis)
These are Milestone E.3 follow-up work (Tasks 24-28 sweeps + future
architectural changes). The composition backtest validated what it
was designed to: the cost-edge frontier of the linear Q + Phase 1d.3
alpha + controller setup, and surfaced the next architectural
question (representation capacity vs action-space size vs fill
realism).
Branch: sp20-aux-h-fixed, pushed.
|
||
|
jgrusewski
|
a36ad53a57 |
feat(alpha): wire slot 543 consumption — 2D threshold × cost sweep
Phase E.3 Task 23 follow-up. Adds the confidence-threshold gate that
consumes the controller's ISV[543] output. Both binaries:
fn epsilon_greedy_gated(q, alpha_confidence, threshold, eps, rng) -> u8 {
if alpha_confidence < threshold { return 0; /* Wait */ }
epsilon_greedy(q, eps, rng)
}
State[1] is the env's alpha_confidence = |sigmoid(alpha_logit) - 0.5|
which is in [0, 0.5]; threshold is also clamped [0, 0.5], so direct
comparison is valid.
alpha_dqn_h600_smoke (closed-loop with controller):
Adds current_threshold: f32 cache, initialised to 0.0 (no gate),
refreshed via stream.clone_dtoh(&isv_dev) after each per-episode
controller invocation. Action selector reads current_threshold for
the NEXT episode's step decisions.
alpha_compose_backtest (2D sweep):
Adds --threshold-grid CLI flag (default [0.0, 0.05, 0.10, 0.15, 0.20,
0.25] — Phase 1d.4 pattern). Eval loop becomes 2D (threshold × cost).
Per-bin includes avg_n_trades for trade-rate visibility. End-of-run
prints BEST per-cost = max Sharpe_ann across τ.
Results (1000 train ep, 300 eval ep × 5 τ × 5 costs):
cost τ=0.00 best τ Sharpe lift trades/ep saved
------- ---------- --------- ----------- ---------------
0.0000 -41.78 -15.72 (τ=0.20) +26.1 477 → 168 (-65%)
0.0625 -71.46 -21.30 (τ=0.25) +50.2 476 → 138 (-71%)
0.1250 -86.78 -29.17 (τ=0.20) +57.6 482 → 167 (-65%)
0.2500 -108.57 -42.12 (τ=0.25) +66.5 480 → 132 (-73%)
0.5000 -146.76 -54.86 (τ=0.25) +91.9 478 → 136 (-72%)
Win rate at cost=0: 7.7% (no gate) → 20.3% (τ=0.20).
The gate architecture is VALIDATED: monotone improvement in win rate +
Sharpe + trade-rate reduction across all costs. The control loop
(controller → slot 543 → policy gate → observed rate feedback) is
sound. But the policy is STILL negative-Sharpe at every cost.
Phase 1d.4 baseline at half-tick: -4.0 (ours: -29.17). 25-pt gap.
Root cause of the remaining gap: the Q-network was TRAINED without
gate awareness. It learned Q-values for the over-trading regime. The
eval-only gate filters those decisions but can't fix miscalibrated
Q-values. Phase 1d.4 baseline beats us because its policy
(always-market-when-confident) is INHERENTLY gated by design — no
mismatched Q-values to fix.
Next iteration to close the 25-pt gap: train WITH gate on, so the
Q-network learns weights for the gated policy class. This means:
either (a) controller runs during training (smoke pattern) and the
threshold develops endogenously, or (b) fixed --train-threshold CLI
during training. Either way, the Q-network sees Wait-at-low-confidence
during the learning phase and adapts.
Files touched:
crates/ml/examples/alpha_dqn_h600_smoke.rs (gate + threshold cache)
crates/ml/examples/alpha_compose_backtest.rs (gate + 2D sweep)
config/ml/alpha_compose_backtest.json (2D verdict)
|
||
|
jgrusewski
|
2af8e02fd8 |
feat(alpha): Phase E.3 composition backtest — reveals slot 543 needs consumption
Phase E.3 Task 23. Trains the Phase E execution-policy DQN on the first
80% of fxcache snapshots, then evaluates the frozen policy (ε=0) on the
held-out 20% across a transaction-cost sweep. Compares absolute Sharpe
vs the Phase 1d.4 always-market-when-confident baseline.
Pipeline pieces:
- Shared loaders extracted into crates/ml/src/env/loaders.rs (used by
both alpha_dqn_h600_smoke and alpha_compose_backtest)
- alpha_compose_backtest.rs: train DQN on first n_train bars, then
frozen-eval n_eval episodes per cost level
- cost grid: [0.0, 0.0625, 0.125, 0.25, 0.5] (price units per
contract round-turn)
- Annualised Sharpe via per-episode Sharpe × sqrt(episodes/year)
where episodes/year ≈ 252 · 6.5h · 3600s / (horizon · 12s)
Run (horizon=600, 1000 train ep, 500 eval ep/cost, 1.5M snapshots):
cost n_ep mean_R std_R Sharpe/ep Sharpe_ann win_rate
0.0000 500 -11.09 8.03 -1.380 -39.50 0.090
0.0625 500 -20.68 9.88 -2.093 -59.89 0.012
0.1250 500 -29.38 9.49 -3.095 -88.58 0.000
0.2500 500 -48.23 11.90 -4.052 -115.98 0.000
0.5000 500 -84.59 17.43 -4.854 -138.92 0.000
Phase 1d.4 baseline for comparison: +4.4 ann. at cost=0, -4.0 at half-tick.
The Phase E policy LOSES MONEY across the whole cost grid — even at
frictionless cost=0. This is not a contradiction with the H=600 PASS
verdict (rvr=+1.04σ): the smoke's rvr is RELATIVE TO RANDOM, while
backtest Sharpe is ABSOLUTE. "Better than random by 1 std" is still
losing if random loses big.
The diagnostic that the E.2 controller already surfaced:
ISV[543] STACKER_THRESHOLD saturated at upper clamp (0.5) — policy
trades 85% of the time vs the 8% target. Over-trading pays spread on
every bar regardless of alpha confidence. Even with perfect alpha
(Phase 1d.3 AUC=0.673), trading 85% × spread cost > alpha edge.
The Phase 1d.4 baseline beats us at cost=0 because it WAITS unless
|stacker_logit| > threshold — the threshold gate filters bars with
weak alpha signal. The Phase E controller PRODUCES slot 543 but the
DQN's action selection doesn't CONSUME it.
This is exactly what the E.3 backtest is FOR: revealing that the
Phase E.1/E.2 producer-side architecture without consumer-side gating
is incomplete. The composition backtest validates the architecture's
weak link.
NEXT (E.3 task 24-28 or a side fix): wire slot 543 consumption into
the action selection. At each step:
if |ISV[543] − 0.5| > |stacker_logit − 0.5|:
action = Wait // confidence below threshold, sit out
else:
action = argmax(Q)
Or equivalently: action = if confidence_high(alpha_logit, ISV[543])
{ argmax(Q) over Buy/Sell actions } else { Wait }.
Once slot 543 is consumed, re-run alpha_compose_backtest and expect
Sharpe to move toward / past the Phase 1d.4 baseline.
Loader refactor: extracted load_fill_model_from_json, load_alpha_cache,
load_snapshots_from_fxcache from alpha_dqn_h600_smoke.rs into
crates/ml/src/env/loaders.rs. The smoke now calls the shared module
via ml::env::loaders::*. ~150 lines of duplicated code removed.
Build + run verified: smoke still builds clean. Backtest runs in ~30s
(train 8s + eval 20s + setup).
Branch: sp20-aux-h-fixed, pushed.
|
||
|
jgrusewski
|
91383507fc |
feat(alpha): wire stacker-threshold controller into smoke rollout-end
Phase E.2 Task 17. Loads stacker_threshold_controller.cubin at smoke
startup, initialises ISV[544] (TRADE_RATE_TARGET) to 0.08 (CLI flag
--trade-rate-target, never reset), allocates a 3-float Wiener state
buffer for slot 545's Pearl A+D state.
Invokes the controller at every episode end with:
rollout_trade_count = count of non-Wait actions in the episode
rollout_total_decisions = actions_host.len() (= ep_len)
rollout_realized_sharpe = ep_terminal_R / RANDOM_BASELINE_STD
(per-rollout analog of the rvr metric;
lets the Kelly-atten controller respond
to in-policy performance vs the baseline
noise floor)
CLI args added:
--trade-rate-target default 0.08 (8% per-step trade rate target)
--k-threshold default 0.01
--k-atten default 0.005
--target-sharpe default 0.5
--wiener-alpha-floor default 0.4
--ctl-alpha-meta default 0.1
Periodic log line extended:
ep ... | KC q/H/rvr/ΔQ ... | CTL thresh=... obs=... atten=...
Final JSON adds:
final_stacker_threshold
final_trade_rate_observed_ema
final_stacker_kelly_attenuation
trade_rate_target
Smoke run (H=600, 1000 episodes) verifies the controller is alive:
ISV[543] STACKER_THRESHOLD: 0.000 → 0.5000 (saturated at ceiling)
ISV[545] TRADE_RATE_OBSERVED_EMA: 0.000 → 0.712
ISV[546] STACKER_KELLY_ATTENUATION:0.000 → 0.100 (hit floor)
Verdict: PASS — rvr=+1.043σ (unchanged from Task 12b PASS, expected
since smoke doesn't yet CONSUME slots 543/546).
Tuning notes (calibration for production, not bugs):
• Threshold saturating at 0.5 → policy trades ~85% (target 8%, off by
10×). Either re-calibrate target_trade_rate from realistic backtest
behaviour, or raise the clamp ceiling. Current ε-greedy with low
threshold-consumption gate produces high trade rate.
• Kelly atten hit floor (0.1) because rollout_sharpe (~-0.004) is far
below target_sharpe=0.5. The target needs to match the rollout
metric's scale, OR the metric should be time-normalised. The
current ep_terminal_R / baseline_std proxy is meaningful but its
scale doesn't match a typical annualised Sharpe target.
These tuning items don't gate Milestone E.2 — the producer-side
controller is correctly driving the ISV slots; *consuming* those slots
(threshold gate on alpha signal, Kelly-cap multiplier) is Phase E.3
work (alpha + execution composition).
Phase E.2 Tasks 16 + 17 close-out: kernel + launcher + GPU smoke test
+ wired into smoke binary + initialisation + verified end-to-end. Tasks
19-22 (NoisyNet) are gated on Task 12 FAIL, which we passed — skipped.
Task 18 (alpha-trust ablation, ~9-18 hours compute) deferred to a
dedicated session if needed.
|
||
|
jgrusewski
|
85792ed28a |
feat(alpha): stacker-threshold + Kelly-attenuation controller kernel
Phase E.2 Task 16. Engagement-rate self-correcting controller per
pearl_engagement_rate_self_correction. Single-block, single-thread
kernel; runs once per rollout-end boundary.
ISV slots driven:
543 STACKER_THRESHOLD_INDEX clamp [0, 0.5] P-controller on rate
545 TRADE_RATE_OBSERVED_EMA_INDEX Pearl A+D floored Wiener-α
546 STACKER_KELLY_ATTENUATION_INX clamp [0.1, 1.0] P-controller on Sharpe
Reads ISV[544] TRADE_RATE_TARGET_INDEX (TrainingPersist anchor, set once
at training start).
Control law:
observed = trade_count / max(decisions, 1)
ISV[545] ← Pearl_A+D_floored(observed, prev, x_lag)
[α* floor = 0.4 per pearl_wiener_alpha_floor_for_nonstationary;
controller co-adapts with policy → need responsive EMA]
err_rate = ISV[545] - ISV[544]
ISV[543] ← clamp(0, 0.5, ISV[543] + k_threshold · err_rate)
err_sharpe = rollout_sharpe - target_sharpe
ISV[546] ← clamp(0.1, 1.0, prev_atten + k_atten · err_sharpe)
where prev_atten = 1.0 if ISV[546] == 0.0 (sentinel-start)
else ISV[546]
Wiener-α is INLINE (not via canonical apply_pearls_ad_kernel chain)
because the EMA is part of the control loop, not a separate diagnostic
slot. Lower latency, fewer kernels per step.
Floor at 0.1 on Kelly attenuation per
pearl_blend_formulas_must_have_permanent_floor — can't be 0, would
zero out position sizing permanently.
Pub launcher `launch_stacker_threshold_controller` in alpha_kernels.rs
with full safety asserts. Slot indices passed as i32 args (decouple
slot numbering from kernel).
GPU smoke test `stacker_threshold_controller_smoke_matches_hand_
computation` verifies 2-iteration sequence:
Iter 1 (Pearl A): observed=0.30 → ISV[545]=0.30; ISV[543]: 0.05 → 0.052
Iter 2 (Pearl D): observed=0.05 → ISV[545]=0.175 (α* hit floor 0.5)
ISV[543]: 0.052 → 0.05275
Both within 1e-5 tolerance. Anchor slot 544 unchanged.
`cargo test -p ml --lib alpha_kernels`: 6 pass (compile witness + 5 GPU
smokes including this one) on RTX 3050 Ti in 2.18s.
Audit doc docs/isv-slots.md updated per Invariant 7.
|
||
|
jgrusewski
|
5c0bcb1fdb |
fix(alpha): MBP-10 parser full-levels copy + fit_poisson L2 regularization
Two carried-over limitations from Phase E.0 / E.1 fixed and verified.
1. MBP-10 parser bug fix (`parse_mbp10_streaming` + `parse_mbp10_file`)
The DBN crate's `Mbp10Msg` carries the FULL post-update top-10 book
in `levels: [BidAskPair; 10]` per message — not just the single
update event's price/size. Previously the parser only called
`update_level(0, ...)` with the update event's fields, leaving
`current_snapshot.levels[1..10]` at default-empty. Downstream:
- OFI calculator reading L2-L5 got zeros → produced wrong OFI
features (the canonical Phase 1c/1d 81-dim feature stack has
multi-level OFI as features 0..5; with the bug these were
constant zero).
- microprice (`snapshot.levels[1]`) got zeros.
- FillModel L2/L3 fit observations got zeros, so L2/L3
coefficients were undefined (we worked around by replicating
L1 with attenuated intercept).
Fix: after `update_level(0, ...)`, copy fields from
`mbp10.levels[lvl]` into `current_snapshot.levels[lvl]` for `lvl
in 1..max_lvl`. Field-by-field copy preserves the existing scale
convention (raw 1e9 fixed-point i64). Applied to both streaming
and async file-parse code paths.
Comment "For simplicity, store all updates in level 0 / A full
implementation would maintain proper level ordering" removed.
2. fit_poisson L2 regularization
New `fit_poisson_l2(features, observed, max_iters, lr, l2_lambda)`
API (the old `fit_poisson` delegates with l2_lambda=0). L2 penalty
applies to slope coefficients β[1..5] but NOT to intercept β[0]
(penalizing the intercept biases toward p≈0.5 for all-zero-feature
samples, breaking the recovery test). Per-iteration update:
β[0] -= lr · grad[0] / n (intercept)
β[k] -= lr · (grad[k] / n + λ · β[k]) (slope, k ∈ 1..5)
Canonical motivation: on real 5.2M-trade ES.FUT data the
unregularized fitter converged to β_spread ≈ -40 (Task 5c commit
|
||
|
jgrusewski
|
79d15b3196 |
chore(alpha): Milestone E.1 H=6000 scale-up — PASS
Phase E.1 Task 13. Same pipeline as the H=600 PASS run (
|
||
|
jgrusewski
|
cd5aa3402b |
feat(alpha): wire Phase 1d.3 stacker into smoke — H=600 VERDICT PASS
Phase E.1 Task 12b complete. The H=600 DQN smoke now consumes real
alpha_logit from the Phase 1d.3 stacker (Mamba2 + 7-input MLP stacker
trained for AUC=0.673 on test), and PASSES all four kill criteria:
Q_SPREAD_EMA = 10.92 ≥ 0.05 PASS
ACTION_ENTROPY_EMA = 1.97 ≥ 1.099 PASS
RETURN_VS_RANDOM_EMA = +1.043 ≥ 0.0 PASS ← jumped +3.62σ
EARLY_Q_MOVEMENT_EMA = 0.099 ≥ 0.01 PASS
Overall: PASS (H=6000 scale-up VIABLE)
Before/after comparison (same env, same DQN, only alpha_logit changed):
alpha_logit=0 alpha_logit=Phase1d.3
rollout_R_mean (final) -18,272 -18
RETURN_VS_RANDOM_EMA -2.58σ +1.04σ
Overall verdict FAIL PASS
The 1000× reduction in episode loss + the +3.62σ rvr swing definitively
proves the "first-best-action lock-in" hypothesis from the previous FAIL
analysis was a SYMPTOM, not the cause. The cause was alpha_logit=0
placeholder starving the policy of directional signal. With real Phase
1d.3 alpha, the linear Q-network learns to use it cleanly — no
NoisyNet, no MLP, no architectural change needed.
Integration pieces in this commit:
1. Cargo workspace registration: ml-alpha added as a workspace dep,
ml's manifest now depends on ml-alpha for FxCacheReader access.
(ml-alpha already depends only on ml-core, so no circular risk.)
2. alpha_dqn_h600_smoke.rs: two new CLI args
--fxcache-path <PATH> load snapshots from precomputed fxcache
(mid from raw_close, bid/ask synthesized
at fixed half-tick, 81-dim features extracted
for spread_bps / l1_imbalance / ofi / mid_drift)
--alpha-cache <PATH> load Phase 1d.3 stacker logit cache produced
by `alpha_train_stacker --alpha-cache-out`.
Each cache entry aligns to the corresponding
fxcache bar, populates SnapshotRow.alpha_logit
(and derives alpha_confidence = |sigmoid(z)-0.5|).
3. Snapshot source selection: in main(), --fxcache-path takes priority
when both paths are set; --alpha-cache requires --fxcache-path
(alignment guarantee). Original --mbp10-dir path unchanged for
non-cached runs.
4. Two new helper fns: load_alpha_cache (binary [u32 n] + [f32; n]
reader), load_snapshots_from_fxcache (FxCacheReader → Vec<SnapshotRow>
with synthesized bid/ask and alpha_logit/alpha_confidence from cache).
alpha_logits_cache.bin (7.6 MB, 1.97M f32 entries) is .gitignore'd —
regenerable from `cargo run -p ml-alpha --release --example
alpha_train_stacker -- --fxcache-path <FXC> --alpha-cache-out
config/ml/alpha_logits_cache.bin` (~2 min on RTX 3050 Ti).
Reproduction of this PASS verdict:
cargo run -p ml --release --example alpha_dqn_h600_smoke -- \
--fxcache-path /home/jgrusewski/Work/foxhunt/test_data/feature-cache/9297....fxcache \
--alpha-cache config/ml/alpha_logits_cache.bin \
--horizon 600 --n-episodes 1000
Total run time ~10s after fxcache load. Verdict + per-checkpoint KC
trajectory in config/ml/alpha_dqn_h600_smoke.json.
NEXT: Task 13 — scale to H=6000 (the production horizon). Per the plan,
PASS at H=600 unlocks H=6000.
|
||
|
jgrusewski
|
5265a0186c |
refactor(alpha): rename phase1*.rs → alpha_*.rs + add --alpha-cache-out
System-scoped naming for the alpha trading system's training binaries — same rationale as the earlier phase_e_* → alpha_* rename. These binaries produce / validate the durable alpha-system components (Mamba2 + stacker + calibration); they're tooling, not milestone artifacts. phase1a.rs → alpha_bar_baseline.rs phase1a_detailed.rs → alpha_bar_detailed.rs phase1d_calibrate.rs → alpha_calibrate.rs phase1d_mamba.rs → alpha_mamba_baseline.rs phase1d_long_horizon.rs → alpha_train_stacker.rs clap `name = "..."` strings updated to match new filenames; cross-refs in docstrings (alpha_calibrate.rs, gbm_baseline.rs) fixed. Plus: NEW `--alpha-cache-out <PATH>` flag on alpha_train_stacker.rs (Phase E.1 Task 12b). After the existing Mamba2 + stacker training completes, runs stacker inference on ALL bars (not just val/test) and dumps the resulting alpha_logits as a little-endian binary file: [u32 n_bars] [f32 logits[n_bars]] Bars `< seq_len − 1` are written as 0.0 (Pearl A sentinel — no history). Inference uses the same Block-S column normalisation (col_mean/col_std) computed during stacker training, applied to all bars consistently. This cache is consumed by alpha_dqn_h600_smoke.rs (next commit) which loads it and populates SnapshotRow.alpha_logit — replacing the current hardcoded 0.0 placeholder with the real Phase 1d.3 stacker output. Build verified: `cargo build -p ml-alpha --release --example alpha_train_stacker` completes clean in 40s. |
||
|
jgrusewski
|
8548d126fd |
chore(alpha): H=600 DQN smoke verdict — FAIL on rvr (linear Q lock-in)
Phase E.1 Task 12. Stabilized H=600 DQN smoke ran end-to-end on full 500K-snapshot data. All three preconditions PASS but the rvr gate FAILS: Q_SPREAD_EMA = 35.54 ≥ 0.05 PASS ACTION_ENTROPY_EMA = 1.91 ≥ 1.099 PASS RETURN_VS_RANDOM_EMA = -2.58 ≥ 0.0 FAIL ← policy WORSE than random EARLY_Q_MOVEMENT_EMA = 0.096 ≥ 0.01 PASS rvr trajectory across 1000 episodes: ep 50 | rollout_R= -11049 | rvr = -1.18 (near random) ep 200 | rollout_R= -9620 | rvr = -0.97 (briefly improving) ep 600 | rollout_R= -18140 | rvr = -2.03 (degrading) ep 1000 | rollout_R= -18272 | rvr = -2.58 (deterministic-bad) Random baseline at H=600 = -5185 mean, std=4953. Trained policy loses 3.5× worse than random. Diagnostics performed: reward_scale=10000 → rvr=-2.37 (no help) alpha_m=0 (vanilla DQN, no Munchausen) → rvr=-2.44 (no help) Root cause: "first-best-action lock-in" of linear Q + ε-greedy. DQN's TD update only modifies Q[a] for the TAKEN action; with ε-decay, the argmax action self-reinforces while other actions' Q stays frozen at random Xavier init. Random policy samples all 9 uniformly → 11% chance of "lucky" close-position at any step → exits bad trades. Trained policy converges deterministic on one bad action → never exits. Per plan: pivot to NoisyNet (Task 19) — parameter-space noise breaks the lock-in. Alternative: wire alpha_logit from Phase 1d.3 stacker (currently hardcoded to 0.0 placeholder) so the policy has actual directional signal to work with. Kill-criteria gate worked as designed — correctly flagged that linear Q + ε-greedy on this env is insufficient without further intervention. Memory note: project_phase_e1_h600_smoke_verdict.md (full analysis + hypothesis tree + recommended next steps). |
||
|
jgrusewski
|
8958637c77 |
feat(alpha): stabilize alpha_dqn_h600_smoke — reward norm + target net + grad clip
Three stabilizers applied to the H=600 DQN smoke after initial run showed
unstable training (early_mvmt=2268× at lr=1e-6, NaN at lr=1e-4):
1. Reward normalization (--reward-scale, default 1000)
Rewards divided by scale BEFORE the Munchausen target. TD error
drops from ~1000 (raw reward magnitude at H=600) into O(1) target /
gradient / weight-update scale. Action selection + rollout-R
reporting use ORIGINAL rewards (so rvr math stays correct against
the Task 7c baseline).
2. Target network (--target-update-every, default 10 episodes)
Separate w_target_dev / b_target_dev buffers. Q_next(s') forward
uses target weights; SGD updates online only. Hard-update copies
online → target every K episodes. Breaks the V_soft(s') chase-its-
own-tail divergence of online-only Munchausen.
3. Gradient clipping (--grad-clip, default 1.0)
New `alpha_clip_inplace_kernel` in alpha_linear_q.cu (element-wise
clamp). Applied to dW and db after grad, before SGD. Safety net.
Diagnostic fix: weight_norm was direction-insensitive — orthogonal
rotations don't change ||W||_F, so early_mvmt read ≈0 even when training.
Switched to weight_distance_from_init = ||W_now − W_init||_F +
||b_now − b_init||_F (captures rotation). q_early = q_init + distance
so kernel's |q_early − q_init| / |q_init| ratio = distance / ||W_init||_F.
With lr bumped back up to 1e-4 (default for the stabilized config),
verified at horizon=100, n_episodes=200:
Q_SPREAD_EMA = 23.64 (≥ 0.05) PASS
ACTION_ENTROPY_EMA = 1.86 (≥ 1.0986) PASS
RETURN_VS_RANDOM_EMA = +0.586 (≥ 0.0) PASS
EARLY_Q_MOVEMENT_EMA = 0.0212 (≥ 0.01) PASS
Overall: PASS (H=6000 scale-up VIABLE)
early_mvmt grew monotonically (0.005 → 0.021) across the 200-episode
run — direction-sensitive diagnostic confirms genuine policy learning.
Audit doc docs/isv-slots.md updated per Invariant 7.
Next: H=600 / 1000-episode run on full data; if PASS holds, Task 13
(H=6000 scale-up) unlocks.
|
||
|
jgrusewski
|
fa30c2dd66 |
feat(alpha): alpha_dqn_h600_smoke — runnable Task 12 DQN smoke
Phase E.1 Task 12. Linear Q-network (W [9×10] + b [9], no hidden layer)
trained with ε-greedy + Munchausen target on the Phase E ExecutionEnv.
End-to-end runnable: load env, train, periodically launch
alpha_kill_criteria + apply_pearls_ad chain at episode boundaries, emit
PASS/FAIL verdict against the 4 kill criteria thresholds.
Pipeline per training step (all on GPU):
1. forward Q_current on s_batch via alpha_linear_q_forward
2. forward Q_next on s'_batch via alpha_linear_q_forward
3. alpha_munchausen_target → targets[batch]
4. alpha_linear_q_grad → dW, db (sparse over taken actions)
5. alpha_linear_q_sgd_step on W and b (separate launches)
6. every K episodes: kill_criteria + apply_pearls_ad chain → ISV[539..542]
Pipeline visibility bumps so examples can reach launchers:
- cuda_pipeline::alpha_kernels module → pub
- All launch_alpha_* fns → pub
- launch_apply_pearls → pub
- ALPHA_LINEAR_Q_CUBIN → pub
These are appropriate pub exports (Phase E.1 public API surface).
Initial micro-smoke (horizon=100, n_episodes=50, lr=1e-6):
Q_SPREAD_EMA = 3.12 (≥ 0.05) PASS
ACTION_ENTROPY_EMA = 2.12 (≥ 1.0986) PASS
RETURN_VS_RANDOM_EMA = +1.03 (≥ 0.0) PASS
EARLY_Q_MOVEMENT_EMA = 2268 (≥ 0.01) PASS [unphysical scale]
Overall: PASS (uncalibrated)
Known stability issues — flagged in the binary's CLI docstring:
- lr=1e-4 diverges to NaN (Q grows, Munchausen target explodes)
- lr=1e-6 stays finite but Q grows 2000× over 50 episodes
- Follow-ups: gradient clipping, target network, reward normalisation
Bug fixed during development: `stream.memcpy_htod(&host, &mut buf.clone())`
was uploading to a TEMPORARY clone (dropped immediately) — `kc_scalar_dev`
and `kc_action_counts_dev` never got their host data → entropy=0, early_mvmt=0,
rvr stuck at the alloc-zeros default. Fixed by removing `.clone()` and using
direct `&mut` refs.
Reads:
config/ml/alpha_fill_coeffs.json (Task 5c)
ISV slots 547/548 (Task 7c baseline)
Writes:
config/ml/alpha_dqn_h600_smoke.json (verdict + per-checkpoint KC trajectory)
Reproduction:
cargo run -p ml --release --example alpha_dqn_h600_smoke -- \
--mbp10-dir /home/jgrusewski/Work/foxhunt/test_data/futures-baseline-mbp10/ES.FUT \
--horizon 600 --n-episodes 1000
Audit doc docs/isv-slots.md updated per Invariant 7.
|
||
|
jgrusewski
|
36ab50814e |
feat(alpha): alpha_linear_q kernels + launchers for Task 12 DQN smoke
Phase E.1 Task 12a. Three new CUDA kernels for the H=600 DQN smoke
(Task 12 proper) that lands in a follow-up commit:
alpha_linear_q_forward_kernel Q = X · W^T + b
alpha_linear_q_grad_kernel dW, db sparse MSE-TD over taken actions
alpha_linear_q_sgd_step_kernel element-wise params -= lr · grad
Architecture: single linear layer, no hidden layer. The Phase E state
vector has meaningful direct features (alpha_logit, spread_bps, position,
ofi_sum_5, …) so linear Q can capture real relations like Q[Buy] ∝
alpha_logit. If linear can't pass the kill-criteria gate, no architecture
upgrade will save it — and the smoke proceeds with NoisyNet escalation
per the plan.
Sparse gradient: only the taken action contributes (standard DQN TD
loss). No atomicAdd needed — one thread per (i, j) loops over the batch
and adds only when actions[b] == i.
GPU contract:
- No host branches inside any kernel (graph-capture compatible)
- No atomicAdd (per feedback_no_atomicadd)
- All compute on GPU (forward, grad, weight update)
- Tiny launch overhead — fits per-step (batch=64 forward = 576 threads,
1 block; grad = 99 threads, 1 block)
Three pub(crate) Rust launchers in alpha_kernels.rs match the
launch_apply_pearls pattern. Cubin embedded via include_bytes!.
Smoke test `linear_q_forward_grad_sgd_round_trip_matches_hand_math`
exercises all three kernels end-to-end on a small (batch=2, state_dim=2,
n_actions=3) case with full hand-math:
Forward: Q = [[2.1, 3.2, 0.3], [4.1, 5.2, 0.3]] ✓
Grad: dW = [[-1.8, -2.7], [0.8, 1.0], [0, 0]]
db = [-0.9, 0.2, 0] ✓
SGD: W' = [[1.18, 0.27], [-0.08, 0.90], [0, 0]]
b' = [0.19, 0.18, 0.30] ✓
All within 1e-4 tolerance. `cargo test -p ml --lib alpha_kernels`:
5/5 pass on RTX 3050 Ti in 2.04s (compile witness + 4 GPU smokes).
Audit doc docs/isv-slots.md updated per Invariant 7.
|
||
|
jgrusewski
|
ebbd28437a |
test(alpha): chained pipeline smoke — Task 12 wiring validation
End-to-end test for the kernel COMPOSITION that the H=600 DQN smoke
(Task 12 proper) will use at each rollout boundary:
t+0 alpha_kill_criteria_compute_kernel → scratch[0..4]
t+1 apply_pearls_ad_kernel(n_slots=4) → ISV[539..543]
The two prior alpha_kernels smokes (munchausen + kill_criteria) validated
kernels in isolation. This smoke validates the COMPOSITION on the same
stream — failures here are different (stream-ordering, Pearls index base,
Wiener offset base, scratch visibility) and would silently break Task 12.
Two iterations with stationary synthetic inputs:
Iter 1 (Pearl A bootstrap)
prev_x_mean=0 AND x_lag=0 → ISV[539..542] populated with raw scratch
observations = [0.2041, 0.8980, 1.0670, 0.1] within 0.01 tolerance.
Anchor slots 547/548 remain at Task 7c values (-5185, 4953).
Iter 2 (Pearl D stationary)
dx_mean = dx_step = 0 → α* = 0 → ISV unchanged from iter 1 within
1e-4. Stationary signal stays at the bootstrap value.
Test would catch:
- Producer's scratch write not visible to applicator (stream-ordering)
- Wrong Pearls isv_idx_base / wiener_offset_base
- Pearl A sentinel detection broken (formula yields 0 at t=0)
- Wiener state corruption (iter 2 drifts from iter 1)
Reuses launch_apply_pearls from sp4_wiener_ema.rs (pub(crate)). Helper
fn run_chained_iter factors the producer→applicator sequence so the two
iterations are byte-identical apart from the Wiener state's evolution.
`cargo test -p ml --lib alpha_kernels`: 4 pass (compile witness + 2 prior
GPU smokes + this chained smoke) on RTX 3050 Ti in 1.89s total. Audit doc
docs/isv-slots.md updated per Invariant 7.
Remaining Task 12 work (full H=600 DQN trainer integration with this
pipeline at rollout boundaries) is queued for a dedicated session.
|
||
|
jgrusewski
|
697bb586d0 |
test(alpha): kill-criteria GPU smoke matching hand-computed observations
Adds the second of the two Phase E.1 kernel smoke tests in
alpha_kernels.rs (companion to the munchausen_target smoke from
|
||
|
jgrusewski
|
91d1a52b9c |
refactor(alpha): rename phase_e_* → alpha_* — system-scoped naming
The kill-criteria producer, Munchausen target kernel, Rust launchers,
fit/baseline binaries, and their output JSON artifacts are *durable
infrastructure* of the alpha trading system (live across Phase E/F/G/...),
not milestone-scoped to Phase E specifically. Aligns with the earlier
`phase_e_isv_slots.rs` → `alpha_isv_slots.rs` rename rationale.
What was renamed:
Code files:
crates/ml/src/cuda_pipeline/phase_e_kill_criteria.cu → alpha_kill_criteria.cu
crates/ml/src/cuda_pipeline/phase_e_munchausen_target.cu → alpha_munchausen_target.cu
crates/ml/src/cuda_pipeline/phase_e_kernels.rs → alpha_kernels.rs
crates/ml/examples/phase_e_fit_fill_model.rs → alpha_fit_fill_model.rs
crates/ml/examples/phase_e_random_baseline.rs → alpha_random_baseline.rs
Artifacts:
config/ml/phase_e_fill_coeffs.json → alpha_fill_coeffs.json
config/ml/phase_e_random_baseline.json → alpha_random_baseline.json
Kernel function names:
phase_e_kill_criteria_compute_kernel → alpha_kill_criteria_compute_kernel
phase_e_munchausen_target_kernel → alpha_munchausen_target_kernel
Rust launcher names:
launch_phase_e_kill_criteria → launch_alpha_kill_criteria
launch_phase_e_munchausen_target → launch_alpha_munchausen_target
Static cubin names:
PHASE_E_MUNCHAUSEN_TARGET_CUBIN → ALPHA_MUNCHAUSEN_TARGET_CUBIN
Historical milestone tags in doc-comments ("Phase E.1 Task N (2026-05-15)")
are RETAINED — they record WHEN the work landed and what plan it
implemented, which doesn't change with the system-scoped rename.
Plus: ADDS the alpha_munchausen_target GPU smoke test in alpha_kernels.rs.
End-to-end validates the launcher + kernel against hand-computed expected
values: batch=2 with one terminal sample; expected targets [29.8, 1.1];
got match within 0.05 tolerance on RTX 3050 Ti. PROVES the Task 9/10
kernels actually run on GPU.
All affected references updated in:
- build.rs (kernel compile list)
- mod.rs (module registration)
- state_reset_registry.rs (4 RegistryEntry descriptions for slots 539-542)
- alpha_isv_slots.rs (slot table comment)
- docs/isv-slots.md (audit-doc cross-references)
Verified:
cargo test -p ml --lib alpha_kernels: 2/2 pass (including GPU smoke)
cargo test -p ml --lib state_reset_registry: 10/10 pass
cargo build -p ml --release --example alpha_fit_fill_model --example alpha_random_baseline: clean
|