AI Paper Atlas

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

A Scale Free Algorithm for Stochastic Bandits with Bounded Kurtosis

Tor Lattimore

NeurIPS 2017 · Bandits and online learning › Multi-armed bandits · approach: Optimal stochastic bandit algorithms

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 a median-of-means UCB with optimistic estimates of both mean and variance, assuming a known finite kurtosis bound\widehat{MM} scale-free UCB · Finite-armed stochastic bandits with bounded kurtosisasymptotic regret: \limsup_{n\to\infty} \frac{\mathcal R_n}{\log(n)} \leq C\sum_{i:\Delta_i > 0} \Delta_i \left(\kappa - 1 + \frac{\sigma^2Improved
Require consistency across subgaussian classes with arbitrary scaleBandit strategies · Non-trivial subgaussian banditslogarithmic regretHurt
Use finite kurtosis as the distributional assumption instead of a known payoff scale or variance parameterScale-free bandit learning · Non-parametric stochastic banditsasymptotic regret: logarithmic regretImproved
Replace median-of-means with Catoni's estimator\widehat{MM} scale-free UCB · Finite-armed stochastic bandits with bounded kurtosisregret constantsImproved

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