arxiv
PublishedJune 1, 2026 at 4:00 AM
Convergence of Steepest Descent and Adam under Non-Uniform Smoothness
Publisher summary· verbatim
arXiv:2605.30648v1 Announce Type: new Abstract: Recent work has analyzed the convergence of first-order methods under non-uniform smoothness assumptions that better model the loss landscape in machine learning tasks. We generalize this assumption to objectives whose curvature is an affine function o
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivSFMambaNet: Spectral-Frequency Enhanced Selective State Space Model for Correspondence Pruning49marxivOptical-Guided Neural Collapse for SAR Few-Shot Class Incremental Learning49marxivDynamic Infilling Anchors for Format-Constrained Generation in Diffusion Large Language Models49marxivTemporal Order Matters for Agentic Memory: Segment Trees for Long-Horizon Agents49mThe Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗