Aspects of discrete mathematics and probability in the theory of machine learning

DOI10.1016/j.dam.2007.05.040zbMath1142.68059OpenAlexW2038271790MaRDI QIDQ2478432

Martin Anthony

Publication date: 28 March 2008

Published in: Discrete Applied Mathematics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.dam.2007.05.040

zbMATH Keywords

concentration of measuremachine learningVapnik-Chervonenkis dimensioncovering numbersuniform Glivenko-Cantelli theorems

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (1)

An improved analysis of the Rademacher data-dependent bound using its self bounding property

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Polynomial bounds for VC dimension of sigmoidal and general Pfaffian neural networks
• Some limit theorems for empirical processes (with discussion)
• The Glivenko-Cantelli problem
• Estimation of dependences based on empirical data. Transl. from the Russian by Samuel Kotz
• Decision theoretic generalizations of the PAC model for neural net and other learning applications
• Existence of submatrices with all possible columns
• Central limit theorems for empirical measures
• Efficient distribution-free learning of probabilistic concepts
• Sphere packing numbers for subsets of the Boolean \(n\)-cube with bounded Vapnik-Chervonenkis dimension
• Concentration inequalities using the entropy method
• A general lower bound on the number of examples needed for learning
• Weak convergence and empirical processes. With applications to statistics
• A combinatorial problem; stability and order for models and theories in infinitary languages
• On the density of families of sets
• 10.1162/153244303768966111
• Learnability and the Vapnik-Chervonenkis dimension
• A theory of the learnable
• Uniform Central Limit Theorems
• Scale-sensitive dimensions, uniform convergence, and learnability
• The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the network
• A sharp concentration inequality with applications
• Structural risk minimization over data-dependent hierarchies
• Neural Network Learning
• Probability Inequalities for Sums of Bounded Random Variables
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
• Convergence of stochastic processes
• Combinatorial methods in density estimation

This page was built for publication: Aspects of discrete mathematics and probability in the theory of machine learning