diff options
| author | YurenHao0426 <Blackhao0426@gmail.com> | 2026-07-22 16:56:13 -0500 |
|---|---|---|
| committer | YurenHao0426 <Blackhao0426@gmail.com> | 2026-07-22 16:56:13 -0500 |
| commit | 380a2a5e56c8edaecb2e0cc1a0bfc592e5b0f72c (patch) | |
| tree | cf10eee298e037aaef1a9d4e759b7c24c0315e50 /ROADMAP.md | |
| parent | 26c257fa528118671a5914f9f9796b24d451839f (diff) | |
docs: close one-sided stability branch
Diffstat (limited to 'ROADMAP.md')
| -rw-r--r-- | ROADMAP.md | 7 |
1 files changed, 7 insertions, 0 deletions
@@ -508,6 +508,13 @@ respectively, with no validation or test evaluation. This narrows any future independent method to operator-level gain control or dissipativity; more endpoint tuning of the same residual-RMS gate is not justified. +The follow-up S0 one-sided stability branch also closes before held-out access. +Its frozen four-margin training-prefix grid has no eligible candidate: small +margins still overflow BN state and grow weights to `1e17`, while larger +margins retain finite tensors but violate loss, signal-ratio, weight, and +momentum envelopes by orders of magnitude. No validation protocol opens. This +rules out fixed sign-only predictor bias as the missing gain-control mechanism. + Prepare convolutional local-update primitives and ResNet-20/32/56 protocols early. Queue frozen runs opportunistically on authorized idle GPUs. Because BurstCCN already reports CIFAR-10 and ImageNet scaling, dataset scale alone is not novel. The oral-level target is a memorable joint |
