AI Paper Atlas

Research map / Bandits and online learning / Online convex optimization and games

Looking Through the Mirror: Minimax-Optimal Regularized Regrets in Online Learning and Bandits

Junghyun Lee, Yujun Kim, Chulhee Yun, Se-Young Yun

NeurIPS 2026 · Bandits and online learning › Online convex optimization and games · approach: Best-of-both-worlds bandit algorithms

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Establishes minimax-optimal regularized regret bounds for online learning and bandits with strongly convex regularizers, under full-information and bandit feedback.

Problem

Regularized regret minimization over the simplex with adversarial rewards and a known strongly-convex regularizer, under full-information and bandit feedback; the minimax regularized regret was not established for a broad regularizer class.

Approach

Derives minimax-optimal regularized regret for a broad class of regularizers that are relatively (strongly) convex with respect to a reference, covering both full-information and bandit settings.

Experimental setup

Metrics: regularized regret

Builds on: mirror descent follow the regularized leader

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy