diff options
| author | YurenHao0426 <Blackhao0426@gmail.com> | 2026-03-24 01:44:34 -0500 |
|---|---|---|
| committer | YurenHao0426 <Blackhao0426@gmail.com> | 2026-03-24 01:44:34 -0500 |
| commit | c09ae4244033a7a2703f0c36279d598ca869a95f (patch) | |
| tree | ac09c1dc29d228865df5796b2a842ca0a42add88 /experiments/topdown_curriculum.py | |
| parent | 8f786597d1007f0ef6012f53c22958d9c4e9b81a (diff) | |
Add CIFAR deltaL test (failed) and pivot design memo
- CIFAR deltaL: s=grad_hL CE (dim=512) -> acc=17.2%, Gamma≈0
Confirms scalar value field has dimensionality bottleneck on CIFAR
- Pivot memo: direct vector credit field a_phi(h,t,s) -> R^d
Trained with perturbation-based target, avoids curvature problem
Still satisfies no hidden BP anchor constraint
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Diffstat (limited to 'experiments/topdown_curriculum.py')
0 files changed, 0 insertions, 0 deletions