summaryrefslogtreecommitdiff
path: root/notes/03_paper_outline.md
diff options
context:
space:
mode:
authorYurenHao0426 <Blackhao0426@gmail.com>2026-05-28 23:19:05 -0500
committerYurenHao0426 <Blackhao0426@gmail.com>2026-05-28 23:19:05 -0500
commit66dc2d38ad8187e111843b911d29b9fc23283aa0 (patch)
treebbd5ffb3f6499b2c122dab7d6d4b7ca9683effc6 /notes/03_paper_outline.md
parent0a3cc65f54d4ffc90b0e73f1f8713820352b27bf (diff)
Add trajectory ensemble validation
Diffstat (limited to 'notes/03_paper_outline.md')
-rw-r--r--notes/03_paper_outline.md1
1 files changed, 1 insertions, 0 deletions
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