AI Paper Atlas

Research map / Bandits and online learning / Multi-armed bandits

Optimal Algorithms for Stochastic Multi-Armed Bandits with Heavy Tailed Rewards

Kyungjae Lee, Hongjun Yang, Sungbin Lim, Songhwai Oh

NeurIPS 2020 · Bandits and online learning › Multi-armed bandits · approach: Optimal stochastic bandit algorithms · 3 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 APE² perturbation exploration instead of robust UCBHeavy-tailed stochastic MAB · Small reward gap, Δ=0.3 or 0.1time-averaged cumulative regretImproved
Use APE² perturbation exploration instead of robust UCBHeavy-tailed stochastic MAB · p=1.5, Δ=0.8time-averaged cumulative regretNo clear effect
Use DSEE's fixed uniform exploration schedule instead of adaptive explorationHeavy-tailed stochastic MAB · Simulated MABtime-averaged cumulative regretHurt
Use the p-robust estimator instead of truncated meanReward estimation with Pareto noise · p=1.5, 1.9, 1.1; λₑ=1.0absolute estimation errorImproved
Use the p-robust estimator instead of truncated meanReward estimation with Pareto noise · p=1.1, λₑ=0.1absolute estimation errorNo clear effect
Use the p-robust estimator instead of median of meansReward estimation with Pareto noise · Simulated estimator convergenceabsolute estimation errorImproved
Use the proposed perturbation strategy despite its slightly slower estimator convergenceAPE² with p=1.1, λₑ=0.1 · Heavy-tailed MABtime-averaged cumulative regretImproved
Use Gumbel or Exponential perturbations rather than the other tested perturbationsAPE² · Simulated heavy-tailed MABtime-averaged cumulative regretImproved

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