diff options
| author | YurenHao0426 <Blackhao0426@gmail.com> | 2026-03-24 01:20:21 -0500 |
|---|---|---|
| committer | YurenHao0426 <Blackhao0426@gmail.com> | 2026-03-24 01:20:21 -0500 |
| commit | e0cbfefc64ac46b6b899ef95f3a90e52e5043390 (patch) | |
| tree | 4e668b71dc1ae6a845d9e82adb450d2630cc7d2b /report_explore/MEMO_10A_prefit_threshold.md | |
| parent | 13668ac1050fee1fa84067fa07c5eaab1a1bc939 (diff) | |
Add Phase 3 boundary-condition ablation results and combined memo
Key findings:
- deltaL (output-layer gradient) gives best Gamma (0.562 vs 0.452 for eT)
- Concatenating h_L to s destroys credit quality (value net cheats)
- Terminal gradient matching is monotonically beneficial
- Best config: deltaL + tgw=1.0 + wr=0.05 -> Gamma=0.768, rho=0.691
- CIFAR depth scan shows no Goldilocks regime (dimensionality bottleneck)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Diffstat (limited to 'report_explore/MEMO_10A_prefit_threshold.md')
0 files changed, 0 insertions, 0 deletions