Measuring the capacity of sets of functions in the analysis of ERM

DOI10.1007/978-3-319-21852-6_16zbMATH Open1336.68223OpenAlexW2289593790MaRDI QIDQ2805728FDOQ2805728

Authors: Ingo Steinwart 

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_16

Recommendations

• Risk bounds for statistical learning
• ERM learning with unbounded sampling
• Local Rademacher complexities and oracle inequalities in risk minimization. (2004 IMS Medallion Lecture). (With discussions and rejoinder)
• ERM learning algorithm for multi-class classification
• Empirical minimization

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cites Work

• Weak convergence and empirical processes. With applications to statistics
• Consistent nonparametric regression. Discussion
• Support Vector Machines
• Title not available (Why is that?)
• Title not available (Why is that?)
• Convergence of stochastic processes
• New concentration inequalities in product spaces
• Title not available (Why is that?)
• Title not available (Why is that?)
• A Bennett concentration inequality and its application to suprema of empirical processes
• A distribution-free theory of nonparametric regression
• Uniform Central Limit Theorems
• Improving the sample complexity using global data
• Title not available (Why is that?)
• Title not available (Why is that?)
• Convexity, Classification, and Risk Bounds
• Combinatorial methods in density estimation
• Gelfand numbers of operators with values in a Hilbert space
• Sphere packing numbers for subsets of the Boolean \(n\)-cube with bounded Vapnik-Chervonenkis dimension
• Optimal aggregation of classifiers in statistical learning.
• Neural Network Learning
• New dependence coefficients. Examples and applications to statistics
• Theory of Classification: a Survey of Some Recent Advances
• Estimating conditional quantiles with the help of the pinball loss
• Fast rates for support vector machines using Gaussian kernels
• Statistical performance of support vector machines
• Rates of convergence for empirical processes of stationary mixing sequences
• Classification with a reject option using a hinge loss
• Consistency of support vector machines for forecasting the evolution of an unknown ergodic dynamical system from observations with unknown noise
• Minimum complexity regression estimation with weakly dependent observations
• Learning from dependent observations
• The generalization performance of ERM algorithm with strongly mixing observations
• The performance bounds of learning machines based on exponentially strongly mixing sequences
• Entropy and the combinatorial dimension
• Scale-sensitive dimensions, uniform convergence, and learnability
• Exponential inequalities and estimation of conditional probabilities
• Any Discrimination Rule Can Have an Arbitrarily Bad Probability of Error for Finite Sample Size
• Optimal concentration inequalities for dynamical systems
• Uniform convergence of Vapnik-Chervonenkis classes under ergodic sampling
• Deviation inequalities for sums of weakly dependent time series
• Oracle inequalities for support vector machines that are based on random entropy numbers
• Fast learning from \(\alpha\)-mixing observations

This page was built for publication: Measuring the capacity of sets of functions in the analysis of ERM

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2805728)