Some connections between learning and optimization

DOI10.1016/J.DAM.2004.06.005MaRDI QIDQ1885804zbMATH OpenOpenAlexFDO

Authors Martin Anthony

Publication date 12 November 2004

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

Full work available at URL https://doi.org/10.1016/j.dam.2004.06.005

zbMATH Keywords

OptimizationLearningComputational complexity of learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Randomized algorithms (68W20) Combinatorial optimization (90C27)

Recommendations

• scientific article; zbMATH DE number 1786133
• scientific article; zbMATH DE number 1664960
• Computational complexity of combinatorial optimization problems induced by collective procedures in machine learning
• The interplay of optimization and machine learning research
• Aspects of discrete mathematics and probability in the theory of machine learning

Cites work

• scientific article; zbMATH DE number 53984 (Why is no real title available?)
• scientific article; zbMATH DE number 3639144 (Why is no real title available?)
• scientific article; zbMATH DE number 1966608 (Why is no real title available?)
• scientific article; zbMATH DE number 1391397 (Why is no real title available?)
• A general lower bound on the number of examples needed for learning
• A theory of the learnable
• Computational limitations on learning from examples
• Cryptographic limitations on learning Boolean formulae and finite automata
• Decision theoretic generalizations of the PAC model for neural net and other learning applications
• Equivalence of models for polynomial learnability
• Estimation of dependences based on empirical data. Transl. from the Russian by Samuel Kotz
• General bounds on the number of examples needed for learning probabilistic concepts
• Hardness results for neural network approximation problems
• Learnability and the Vapnik-Chervonenkis dimension
• Neural Network Learning
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
• Robust trainability of single neurons
• Sharper bounds for Gaussian and empirical processes
• The densest hemisphere problem
• Toward efficient agnostic learning

Cited in

(8)

• scientific article; zbMATH DE number 1786133 (Why is no real title available?)
• How can machine learning and optimization help each other better?
• Machine learning and combinatorial optimization. Editorial
• Machine learning problems from optimization perspective
• Theoretical connections between optimization algorithms based on an approximate gradient
• scientific article; zbMATH DE number 1664960 (Why is no real title available?)
• From numerical optimization method to learning optimization method
• Discovering optimization algorithms through automated learning

This page was built for publication: Some connections between learning and optimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1885804)