On the necessity of adaptive regularisation: Optimal anytime online learning on $\boldsymbol{\ell_p}$-balls

NeurIPSSpotlight2025

Authors
Emmeran Johnson, David Martínez-Rubio, Ciara Pike-Burke, Patrick Rebeschini
Venue
NeurIPS 2025
Track
Spotlight

TL;DR

We study online convex optimization on $\ell_p$-balls in $\mathbb{R}^d$ for $p > 2$…

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

optimization

Related NeurIPS papers

← All NeurIPS 2025 Spotlight papers · Browse the whole archive