Prediction, learning, uniform convergence, and scale-sensitive dimensions

DOI10.1006/jcss.1997.1557zbMath0945.68529OpenAlexW2071570468MaRDI QIDQ1271550

Philip M. Long, Bartlett, Peter L.

Publication date: 27 September 2000

Published in: Journal of Computer and System Sciences (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1006/jcss.1997.1557

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (8)

Efficient algorithms for learning functions with bounded variation ⋮ On the complexity of learning from drifting distributions ⋮ The learnability of quantum states ⋮ Corrigendum to: ``Prediction, learning, uniform convergence, and scale-sensitive dimensions ⋮ Learning bounds for quantum circuits in the agnostic setting ⋮ The generalization performance of ERM algorithm with strongly mixing observations ⋮ Using the doubling dimension to analyze the generalization of learning algorithms ⋮ Unnamed Item

Cites Work

• Learnability with respect to fixed distributions
• Equivalence of models for polynomial learnability
• Decision theoretic generalizations of the PAC model for neural net and other learning applications
• Efficient distribution-free learning of probabilistic concepts
• Predicting \(\{ 0,1\}\)-functions on randomly drawn points
• Toward efficient agnostic learning
• Sphere packing numbers for subsets of the Boolean \(n\)-cube with bounded Vapnik-Chervonenkis dimension
• A general lower bound on the number of examples needed for learning
• Fat-shattering and the learnability of real-valued functions
• Learnability and the Vapnik-Chervonenkis dimension
• Scale-sensitive dimensions, uniform convergence, and learnability
• Convergence of stochastic processes

This page was built for publication: Prediction, learning, uniform convergence, and scale-sensitive dimensions