diff options
| author | YurenHao0426 <Blackhao0426@gmail.com> | 2026-05-28 23:10:22 -0500 |
|---|---|---|
| committer | YurenHao0426 <Blackhao0426@gmail.com> | 2026-05-28 23:10:22 -0500 |
| commit | 89ebbd7ba50321e790520522939a941ff5ea96b7 (patch) | |
| tree | 4ed8144ae1de4c3f8c6cf7235350040fc6903aad /notes/03_paper_outline.md | |
| parent | 2446bb758f6ec7456c1279e6b8ea5ebda9530cc3 (diff) | |
Add synthetic FA trajectory validation
Diffstat (limited to 'notes/03_paper_outline.md')
| -rw-r--r-- | notes/03_paper_outline.md | 6 |
1 files changed, 6 insertions, 0 deletions
diff --git a/notes/03_paper_outline.md b/notes/03_paper_outline.md index 829226d..a8f07c8 100644 --- a/notes/03_paper_outline.md +++ b/notes/03_paper_outline.md @@ -171,6 +171,12 @@ Trajectory: - \(Q_l(t)\), \(\Gamma_t\), and \(\Delta L_T\). - redundancy-exhaustion transition. +Initial implementation note: + +- Start with synthetic full-batch regression and no-bias MLPs. +- Record same-point gradient alignment by computing BP and FA gradients at the FA weights. +- Treat early trajectory runs as instrumentation checks before drawing distributional conclusions. + ## 9. Discussion Key points: |