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

DOI10.1007/978-3-319-21852-6_15zbMATH Open1357.68181OpenAlexW2309498013MaRDI QIDQ2805727FDOQ2805727

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

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

Mathematics Subject Classification ID

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

Cites Work

• Weak convergence and empirical processes. With applications to statistics
• Title not available (Why is that?)
• Prediction, Learning, and Games
• Aggregation via empirical risk minimization
• Learning by mirror averaging
• Convergence of stochastic processes
• Uniform Central Limit Theorems
• Martingales with values in uniformly convex spaces
• The weighted majority algorithm
• The importance of convexity in learning with squared loss
• How to use expert advice
• On the Generalization Ability of On-Line Learning Algorithms
• Title not available (Why is that?)
• Empirical discrepancies and subadditive processes
• Efficient distribution-free learning of probabilistic concepts
• Entropy and the combinatorial dimension
• Scale-sensitive dimensions, uniform convergence, and learnability
• Combinatorics of random processes and sections of convex bodies
• Fat-shattering and the learnability of real-valued functions

Cited In (8)

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

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)