Fat-shattering and the learnability of real-valued functions

DOI10.1006/jcss.1996.0033zbMath0858.68076OpenAlexW4252305909MaRDI QIDQ1924381

Robert C. Williamson, Philip M. Long, Bartlett, Peter L.

Publication date: 26 November 1996

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

Full work available at URL: https://doi.org/10.1006/jcss.1996.0033

zbMATH Keywords

Vapnik-Chervonenkis dimensionlearnability

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (15)

Approximation and learning of convex superpositions ⋮ Benefit of Interpolation in Nearest Neighbor Algorithms ⋮ On the value of partial information for learning from examples ⋮ The learnability of quantum states ⋮ A computational learning theory of active object recognition under uncertainty ⋮ Robust regression using biased objectives ⋮ Sequential complexities and uniform martingale laws of large numbers ⋮ On Martingale Extensions of Vapnik–Chervonenkis Theory with Applications to Online Learning ⋮ Scale-sensitive dimensions and skeleton estimates for classification ⋮ Prediction, learning, uniform convergence, and scale-sensitive dimensions ⋮ New bounds on classical and quantum one-way communication complexity ⋮ Efficient learning with robust gradient descent ⋮ Distribution-free consistency of empirical risk minimization and support vector regression ⋮ Unnamed Item ⋮ Rates of uniform convergence of empirical means with mixing processes

This page was built for publication: Fat-shattering and the learnability of real-valued functions