Learning with stochastic inputs and adversarial outputs

DOI10.1016/j.jcss.2011.12.027zbMath1244.68067MaRDI QIDQ439998

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

zbMATH Keywords

online learning; hybrid stochastic-adversarial learning

Mathematics Subject Classification ID

62H30: Classification and discrimination; cluster analysis (statistical aspects)

68T05: Learning and adaptive systems in artificial intelligence

Related Items

Sensor networks: from dependence analysis via matroid bases to online synthesis

Cites Work

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