Rigorous learning curve bounds from statistical mechanics

DOI10.1007/BF00114010zbMath0870.68131OpenAlexW4253803546MaRDI QIDQ676243

Michael Kearns, David Haussler, H. Sebastian Seung, Naftali Tishby

Publication date: 6 May 1997

Published in: Machine Learning (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/bf00114010

zbMATH Keywords

phase transitionsstatistical mechanicslearning curves

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items

Characterizing rational versus exponential learning curves, Unnamed Item, Results in statistical discriminant analysis: A review of the former Soviet Union literature., Unnamed Item, A random matrix analysis of random Fourier features: beyond the Gaussian kernel, a precise phase transition, and the corresponding double descent*

Cites Work

• Unnamed Item
• Unnamed Item
• Learnability with respect to fixed distributions
• 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
• Central limit theorems for empirical measures
• Bounds on the sample complexity of Bayesian learning using information theory and the VC dimension
• A general lower bound on the number of examples needed for learning
• The space of interactions in neural network models
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
• Convergence of stochastic processes