Probably Approximate Learning over Classes of Distributions

DOI10.1137/0221029zbMATH Open0761.68080OpenAlexW2042672920MaRDI QIDQ4016907FDOQ4016907

Authors B. K. Natarajan 

Publication date 16 January 1993

Published in SIAM Journal on Computing (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1137/0221029

zbMATH Keywords

setsfunctionsprobabilistic learningclasses of distributions

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Nonparametric inference (62G99)

Recommendations

• Probably Approximate Learning of Sets and Functions
• On the learnability of discrete distributions
• On the learnability of rich function classes
• Learnability with respect to fixed distributions
• Efficient distribution-free learning of probabilistic concepts

Cited In (17)

• Implementing Valiant's learnability theory using random sets.
• On Learning Functions from Noise-Free and Noisy Samples via Occam's Razor
• Equivalences between learning of data and probability distributions, and their applications
• Learning from rounded-off data.
• Efficient distribution-free population learning of simple concepts
• Probably almost discriminative learning
• Learnability with respect to fixed distributions
• Embedding sample points uncertainty measures in learning algorithms
• Learning Structure Illuminates Black Boxes – An Introduction to Estimation of Distribution Algorithms
• Decision theoretic generalizations of the PAC model for neural net and other learning applications
• Learning dynamical systems in a stationary environment
• Learning distributions by their density levels: A paradigm for learning without a teacher
• Lifting uniform learners via distributional decomposition
• Sample size lower bounds in PAC learning by Algorithmic Complexity Theory
• Valid Generalisation from Approximate Interpolation
• PAC learning of probability distributions over a discrete domain.
• Probably Approximate Learning of Sets and Functions

This page was built for publication: Probably Approximate Learning over Classes of Distributions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4016907)