DM
David Mart\'inez-Rubio, Brian Bullins, Crist\'obal Guzm\'an, Mathieu Molina
· 1 min read
ResearcharXiv cs.LG
Near-Optimal Acceleration for Smooth $\ell_p$ / $\ell_q$ Nondual Convex First-Order Oracle Optimization
arXiv:2609.21880v1 Announce Type: cross
Abstract: We study the optimization of convex objectives with $(L,\kappa-1)$-H\"older-continuous gradients in $\ell_q$ over $R B_p^d$, $1<\kappa\le 2$. (MG26) provides selectors with a movement bound for the problem of chasing high-dimensional convex nested sets for every $p
Original source
This story was published by arXiv cs.LG and written by David Mart\'inez-Rubio, Brian Bullins, Crist\'obal Guzm\'an, Mathieu Molina. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org
