On martingale extensions of Vapnik-Chervonenkis theory with applications to online learning

DOI10.1007/978-3-319-21852-6_15MaRDI QIDQ2805727zbMATH OpenOpenAlexFDO

Authors Alexander Rakhlin, Karthik Sridharan

Publication date 13 May 2016

Published in Measures of Complexity (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/978-3-319-21852-6_15

Mathematics Subject Classification ID

Martingales with discrete parameter (60G42) Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• scientific article; zbMATH DE number 1569102
• On the Generalization Ability of On-Line Learning Algorithms
• Online learning via sequential complexities
• scientific article; zbMATH DE number 7564348
• Sequential complexities and uniform martingale laws of large numbers

Cites work

• Aggregation via empirical risk minimization
• Combinatorics of random processes and sections of convex bodies
• Convergence of stochastic processes
• Efficient distribution-free learning of probabilistic concepts
• Empirical discrepancies and subadditive processes
• Entropy and the combinatorial dimension
• Fat-shattering and the learnability of real-valued functions
• How to use expert advice
• scientific article; zbMATH DE number 3738628 (Why is no real title available?)
• scientific article; zbMATH DE number 823069 (Why is no real title available?)
• Learning by mirror averaging
• Martingales with values in uniformly convex spaces
• On the Generalization Ability of On-Line Learning Algorithms
• Prediction, Learning, and Games
• Scale-sensitive dimensions, uniform convergence, and learnability
• The importance of convexity in learning with squared loss
• The weighted majority algorithm
• Uniform Central Limit Theorems
• Weak convergence and empirical processes. With applications to statistics

Cited in

(8)

• A sieve stochastic gradient descent estimator for online nonparametric regression in Sobolev ellipsoids
• Machine learning advised ski rental problem with a discount
• Rademacher complexity for Markov chains: applications to kernel smoothing and Metropolis-Hastings
• Stochastic online optimization. Single-point and multi-point non-linear multi-armed bandits. Convex and strongly-convex case
• Approachability, regret and calibration: implications and equivalences
• Active learning for cost-sensitive classification
• Online learning via sequential complexities
• Minimax rates for conditional density estimation via empirical entropy

This page was built for publication: On martingale extensions of Vapnik-Chervonenkis theory with applications to online learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2805727)