diff options
| author | YurenHao0426 <Blackhao0426@gmail.com> | 2026-06-09 15:30:20 -0500 |
|---|---|---|
| committer | YurenHao0426 <Blackhao0426@gmail.com> | 2026-06-09 15:30:20 -0500 |
| commit | 84fa70be406248e660488ddc4c56ca5ea0034189 (patch) | |
| tree | 828e47ecd89991c2b446a0d0a6f5c030c7348e12 /notes/README.md | |
| parent | b246cc878c3db48e6d993a6a293176ee9be97e77 (diff) | |
Add teacher-task test-gap sweep and figure
SGD teacher sweep (widths 8-96, 24 FA runs/width): train gap soft and
monotone (0.249 -> 0.0069) while the test gap changes sign — FA
generalizes better than BP at intermediate width (-0.120 +/- 0.013 at
w=32) and settles slightly positive once both fit. Scopes the paper's
optimization-gap claims and preempts the generalization question.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Diffstat (limited to 'notes/README.md')
| -rw-r--r-- | notes/README.md | 4 |
1 files changed, 4 insertions, 0 deletions
diff --git a/notes/README.md b/notes/README.md index 158a8c5..76d8e46 100644 --- a/notes/README.md +++ b/notes/README.md @@ -10,6 +10,10 @@ Use this directory as the project memory. Keep rough ideas here before promoting - [36_evidence_ledger.md](36_evidence_ledger.md): **the writing base** — full evidence chain, corrected headline numbers, figure sources, claim discipline. +- [38_mnist_real_data_validation.md](38_mnist_real_data_validation.md): e0 + theorem + estimator replicated on MNIST (no fit). +- [39_teacher_test_gap.md](39_teacher_test_gap.md): teacher-task test gap — + optimization cost invariant, test effect task-dependent (sign flip). - [37_wrapup_corrections.md](37_wrapup_corrections.md): pre-writing audit fixes (e0 sampler now real FA backward; closed-form comparison now data/init-matched — corr 0.977 retired, 0.933 matched / 0.982 ensemble). |