diff options
| author | YurenHao0426 <Blackhao0426@gmail.com> | 2026-05-23 04:45:03 -0500 |
|---|---|---|
| committer | YurenHao0426 <Blackhao0426@gmail.com> | 2026-05-23 04:45:03 -0500 |
| commit | d11a0f6432e26c3243123d5e19aaf2702c76d64c (patch) | |
| tree | 6e4d55e99e65a01acf47dda4a12da1089622849b /scripts/train_hrm_orth.py | |
| parent | 27b69c2b75a251ec39ece318c26ccb1a25d9fd79 (diff) | |
SRM-AOL: codex review fixes
- Soften exact Lipschitz claim — bf16 cast makes bound approximate (only exact in fp32)
- BlockGain init_diag 1.0 → 3.0: original gave 27% cross-coupling (mislabeled "minimal");
3.0 gives ~5% which is what "minimal" should mean
- Note torch.compile risk with linalg.solve in CayleyOrthogonal
Per codex review of v1.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Diffstat (limited to 'scripts/train_hrm_orth.py')
0 files changed, 0 insertions, 0 deletions