jgrusewski b88fd62af2 feat(ml): add Diffusion model (DDPM/DDIM) for price path generation ...

- NoiseScheduler: precomputed cosine/linear alpha_bar schedules
- Denoiser: FC network with sinusoidal time embedding + SiLU + residual
- DDIMSampler: deterministic fast sampling (10 steps from 1000 timesteps)
- DiffusionTrainableAdapter: UnifiedTrainable for unified training pipeline
- Hyperopt adapter with ParameterSpace (9 params, batch ≤64 for 4GB GPU)
- ModelType::Diffusion registered in common + coordinator
- 41 tests passing (config=3, noise=7, denoiser=4, sampler=5, trainable=12, hyperopt=7)
- OOM-safe: FC denoiser instead of U-Net, small hidden dims, conservative defaults

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-02-23 09:32:44 +01:00

..

coordinator.rs

feat(ml): add Diffusion model (DDPM/DDIM) for price path generation

2026-02-23 09:32:44 +01:00

distillation.rs

refactor(ml): remove 797 lines of commented-out code and disabled imports

2026-02-20 19:43:47 +01:00

inference_engine.rs

cleanup(ml): remove 31 disabled imports and commented-out module blocks

2026-02-20 18:23:41 +01:00

mod.rs

cleanup(ml): remove 31 disabled imports and commented-out module blocks

2026-02-20 18:23:41 +01:00

model_registry.rs

cleanup(ml): remove 31 disabled imports and commented-out module blocks

2026-02-20 18:23:41 +01:00

performance_monitor.rs

cleanup(ml): remove 31 disabled imports and commented-out module blocks

2026-02-20 18:23:41 +01:00

strategy_dqn_bridge.rs

refactor: consolidate DQNConfig to single canonical definition

2026-02-22 20:49:22 +01:00