generated from mathias/template-go-web
b2bc01ba9ea955c13e2b4e02dcc8077ce0ed7988
Two-phase phase-1: 1a. Frozen warmup: head trains on pre-computed embeddings for PHASE1_EPOCHS=200 1b. Joint fine-tune: encoder + head for PHASE1_JOINT_EPOCHS=30 at PHASE1_ENCODER_LR=3e-6 Key design decisions: - Warm start prevents catastrophic forgetting (PHASE1_JOINT=1 cold-start → -32 R²) - Normalize live encoder output with FROZEN stats (mu_e/sd_e) so head sees same embedding distribution it was warmed up on - head LR reduced 10× in joint phase to prevent head from racing ahead HPO sweep: 30ep@3e-6=0.3962, 30ep@1e-5=0.3930, 50ep@3e-6=0.3923 Baseline (frozen): 0.3908. New best: phase1_r2=0.3962 (+0.0054 OOS). New knobs: JEPA_PHASE1_JOINT (default 1), JEPA_PHASE1_JOINT_EPOCHS (default 30), JEPA_PHASE1_ENCODER_LR (default 3e-6). 4 new tests (tests 15-18). 28/28 pass. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
hostexecutor
Generated from
mathias/template-go-web.
Bootstrap
After creating from template, run:
go mod tidy # regenerate go.sum with real module path
task generate # generate templ files
task build # build the binary
Description
JEPA-based latent representation learning for FX trading risk management — research project
370 KiB
Languages
Python
76.4%
Go
18.4%
Shell
4.3%
templ
0.6%
Dockerfile
0.3%