From 66dc2d38ad8187e111843b911d29b9fc23283aa0 Mon Sep 17 00:00:00 2001 From: YurenHao0426 Date: Thu, 28 May 2026 23:19:05 -0500 Subject: Add trajectory ensemble validation --- notes/03_paper_outline.md | 1 + 1 file changed, 1 insertion(+) (limited to 'notes/03_paper_outline.md') diff --git a/notes/03_paper_outline.md b/notes/03_paper_outline.md index a8f07c8..65a5c47 100644 --- a/notes/03_paper_outline.md +++ b/notes/03_paper_outline.md @@ -176,6 +176,7 @@ 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. +- Use within-architecture correlations as the first trajectory validation target; pooled correlations can be misleading because architecture-level task difficulty and BP final loss vary. ## 9. Discussion -- cgit v1.2.3