Corruption-tolerant bandit learning

DOI10.1007/S10994-018-5758-5MaRDI QIDQ669323zbMATH OpenOpenAlexFDO

Authors Sayash Kapoor, Kumar Kshitij Patel, Purushottam Kar

Publication date 15 March 2019

Published in Machine Learning (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s10994-018-5758-5

zbMATH Keywords

bandit algorithmsonline learningrobust learning

Mathematics Subject Classification ID

Compound decision problems in statistical decision theory (62C25) Learning and adaptive systems in artificial intelligence (68T05) Online algorithms; streaming algorithms (68W27)

Recommendations

• Stochastic bandits robust to adversarial corruptions
• Corrupt bandits for preserving local privacy
• Algorithms for adversarial bandit problems with multiple plays
• The Nonstochastic Multiarmed Bandit Problem
• scientific article; zbMATH DE number 6253908

Cites work

• Bandits With Heavy Tail
• Corrupt bandits for preserving local privacy
• Exact Recoverability From Dense Corrupted Observations via $\ell _{1}$-Minimization
• Exploration-exploitation tradeoff using variance estimates in multi-armed bandits
• Finite-time analysis of the multiarmed bandit problem
• scientific article; zbMATH DE number 3320125 (Why is no real title available?)
• Introduction to nonparametric estimation
• Learning from untrusted data
• Robust Estimation of a Location Parameter
• Robust estimators in high-dimensions without the computational intractability
• Robust principal component analysis?
• Robust Statistics
• Robustly learning a Gaussian: getting optimal error, efficiently
• Stochastic bandits robust to adversarial corruptions
• The Nonstochastic Multiarmed Bandit Problem
• Tuning Bandit Algorithms in Stochastic Environments

Cited in

(11)

• Secure cumulative reward maximization in linear stochastic bandits
• Negatively Correlated Bandits
• Corrupt bandits for preserving local privacy
• scientific article; zbMATH DE number 7370589 (Why is no real title available?)
• Best arm identification for contaminated bandits
• Stochastic bandits robust to adversarial corruptions
• Contextual Search in the Presence of Adversarial Corruptions
• A new bandit setting balancing information from state evolution and corrupted context
• Robust matroid bandit optimization: near-optimal rates under adversarial contamination
• Robust matroid bandit optimization against adversarial contamination
• CRIMED: lower and upper bounds on regret for bandits with unbounded stochastic corruption

Describes a project that uses

Uses Software

• robustbase

This page was built for publication: Corruption-tolerant bandit learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q669323)