Critical initialization destabilizes higher input derivatives in wide scalar-input networks
This story is from 2026-09-10. It is preserved in the archive; the latest stories are on the live feed.
arXiv:2609.09244v1 Announce Type: new Abstract: The edge-of-chaos condition preserves first-order input perturbations in wide randomly initialized networks, but physics-informed losses, score matching and derivative regularization depend on higher input derivatives. For smooth scalar-input fully co…
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-09-10 04:00 · arXiv stat.ML
Critical initialization destabilizes higher input derivatives in wide scalar-input networks