AI Paper Atlas

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

Minimax Optimal Quantile and Semi-Adversarial Regret via Root-Logarithmic Regularizers

Jeffrey Negrea, Blair Bilodeau, Nicolò Campolongo, Francesco Orabona, Daniel M. Roy

NeurIPS 2021 · Bandits and online learning › Online convex optimization and games · approach: Best-of-both-worlds bandit algorithms · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use the root-logarithmic regularizer instead of Hedge's Shannon-entropy regularizerFTRL for KL regret · KL regret with arbitrary priorsregret bound dependence on comparator KL: 2 \sqrt{(T+1)(1 + \KL{q}{\nu})} + \sqrt{8T}Improved
Use the root-logarithmic regularizer with a uniform priorabNormal · Quantile regret (N experts)regret rate: \sqrt{T\log(1/\epsilon)}Improved
Use CARL's expert-specific effective regularization through the -H_C regularizerFTRL-CARL · Semi-adversarial regret, N_{0}>1expected regret upper bound: \sqrt{2T\logN_{0}} + 25\frac{\logN}{\Delta_{0}}Improved
Use FTRL-CARL instead of FTRL-CARESemi-adversarial learning with expert advice · Semi-adversarial regret at small Texpected regret upper bound: \sqrt{2T\logN}Improved

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