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/35_current_results_consolidated.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/35_current_results_consolidated.md')
0 files changed, 0 insertions, 0 deletions