diff options
| author | YurenHao0426 <Blackhao0426@gmail.com> | 2026-07-22 16:38:42 -0500 |
|---|---|---|
| committer | YurenHao0426 <Blackhao0426@gmail.com> | 2026-07-22 16:38:42 -0500 |
| commit | 575530e7124c540e58571b50ef147a5f20e6cb54 (patch) | |
| tree | c1058abde90f59d2e9b594661f1794b6e974ae18 /ROADMAP.md | |
| parent | d818fc26cdcbc00521e4cd4e347e74d5cd3e5670 (diff) | |
docs: explain mixed-traffic instability
Diffstat (limited to 'ROADMAP.md')
| -rw-r--r-- | ROADMAP.md | 6 |
1 files changed, 6 insertions, 0 deletions
@@ -502,6 +502,12 @@ checks pass while all performance, finite, alignment, and tracking checks fail. Per the frozen stop rule, MT-2 and MT-3 remain untouched, no weaker traffic ratio is allowed, and this standard-ResNet accept path closes at 5/10. +The training-only post-failure audit localizes the common instability to stem +`W[0]` and its momentum at steps 23/69/74 for raw/matched/innovation, +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. + 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 |
