diff options
| author | YurenHao0426 <Blackhao0426@gmail.com> | 2026-03-25 16:20:53 -0500 |
|---|---|---|
| committer | YurenHao0426 <Blackhao0426@gmail.com> | 2026-03-25 16:20:53 -0500 |
| commit | 5a3b20d627eca65612f598c1ba5807d5d2df029a (patch) | |
| tree | e7f2f697303f738e757db6e93214d880f6c7642a /experiments/cifar_depth_scan.py | |
| parent | 3ec9a5cd63b4578999d89b49f5223024a1acb723 (diff) | |
Add Phase 9A: checkpointed handoff — blend(Vec+DFA) outperforms pure DFA
First positive online result: 50% blend of offline-fitted Vec + DFA gives 31.7%
vs 31.1% for pure DFA (+0.55%). This is Case B: pure Vec handoff fails (-1.1%)
but blend works because DFA stabilizes trajectory while Vec adds directional credit.
Offline-fitted Vec at DFA epoch-5 checkpoint: Gamma=0.229, rho=0.262.
Cold-start confirmed as main bottleneck — Vec IS useful on DFA trajectory features.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Diffstat (limited to 'experiments/cifar_depth_scan.py')
0 files changed, 0 insertions, 0 deletions