diff options
Diffstat (limited to 'NOTE.md')
| -rw-r--r-- | NOTE.md | 24 |
1 files changed, 23 insertions, 1 deletions
@@ -5,7 +5,7 @@ - **pilot**: Controlled iteration (commits 0b9ebb2, 7baf7ae) - **frozen**: Code at commit 0b9ebb2 for all reported results -## Status: PHASE 8 SCHEDULE TIMING — ONLINE CO-LEARNING IS THE REMAINING BOTTLENECK +## Status: PHASE 9A — BLEND HANDOFF OUTPERFORMS DFA (+0.55%) --- @@ -484,3 +484,25 @@ is ready, the early window is closed. ### Experiment IDs (Phase 8) - `schedule_timing/`: Phase 8 schedule comparison + +--- + +## Phase 9A: Checkpointed Offline Handoff + +**Setup**: DFA trajectory with checkpoint at t0=5 (acc=30.4%). +Offline-fit Vec_M4 on frozen checkpoint (60 epochs). Then branch. + +| Branch | final acc | diff vs DFA | +|--------|-----------|-------------| +| continue_DFA | 0.311 | baseline | +| handoff_to_Vec | 0.300 | -0.011 | +| **handoff_blend_05** | **0.317** | **+0.006** | + +**FIRST POSITIVE ONLINE RESULT**: 50% blend (Vec+DFA) outperforms pure DFA by +0.55%. + +This is Case B: pure Vec handoff fails, but blend works. +Vec provides complementary directional credit that DFA alone lacks. +DFA stabilizes the trajectory while Vec adds learned corrections. + +### Experiment IDs (Phase 9) +- `checkpointed_handoff/`: Phase 9A checkpointed handoff with branches |