Learning with stochastic inputs and adversarial outputs

DOI10.1016/J.JCSS.2011.12.027zbMATH Open1244.68067OpenAlexW2153068585MaRDI QIDQ439998FDOQ439998

Authors: Alessandro Lazaric, Rémi Munos 

Publication date: 17 August 2012

Published in: Journal of Computer and System Sciences (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.jcss.2011.12.027

Recommendations

• scientific article; zbMATH DE number 7064063
• Learning hurdles for sleeping experts
• Partial monitoring -- classification, regret bounds, and algorithms
• How to better use expert advice
• Learning hurdles for sleeping experts

zbMATH Keywords

online learninghybrid stochastic-adversarial learning

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05)

Cites Work

• Prediction, Learning, and Games
• Convergence of stochastic processes
• On the density of families of sets
• A distribution-free theory of nonparametric regression
• The Nonstochastic Multiarmed Bandit Problem
• The weighted majority algorithm
• 10.1162/153244303321897663
• Advanced Lectures on Machine Learning
• How to use expert advice
• Smoothed analysis of algorithms
• 10.1162/jmlr.2003.3.4-5.951
• Pattern recognition for conditionally independent data
• Learning correlated equilibria in games with compact sets of strategies
• Learning Theory
• A game of prediction with expert advice
• Scale-sensitive dimensions, uniform convergence, and learnability
• Decision theoretic generalizations of the PAC model for neural net and other learning applications
• Characterizations of learnability for classes of \(\{0,\dots,n\}\)-valued functions

Cited In (4)

• Universal regression with adversarial responses
• Sensor networks: from dependence analysis via matroid bases to online synthesis
• On biased random walks, corrupted intervals, and learning under adversarial design
• Stochastic bandits robust to adversarial corruptions

This page was built for publication: Learning with stochastic inputs and adversarial outputs

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q439998)