The entropy in learning theory. Error estimates

DOI10.1007/S00365-006-0633-8MaRDI QIDQ854989zbMATH OpenOpenAlexFDO

Authors Sergei Konyagin, V. N. Temlyakov

Publication date 20 December 2006

Published in Constructive Approximation (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s00365-006-0633-8

Mathematics Subject Classification ID

Statistical aspects of information-theoretic topics (62B10) Nonparametric regression and quantile regression (62G08) Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Optimal estimators in learning theory
• Bounds on margin distributions in learning problems
• Local entropy in learning theory
• Learning theory estimates via integral operators and their approximations
• On universal estimators in learning theory

Cited in

(22)

• Approximation by neural networks and learning theory
• Universal discretization
• Thresholding in learning theory
• \(L_2\)-norm sampling discretization and recovery of functions from RKHS with finite trace
• Adaptive estimation for nonlinear systems using reproducing kernel Hilbert spaces
• A remark on entropy numbers
• Sampling discretization of integral norms of the hyperbolic cross polynomials
• Marcinkiewicz-type discretization of \(L^p\)-norms under the Nikolskii-type inequality assumption
• On universal estimators in learning theory
• Optimal estimators in learning theory
• Weak thresholding greedy algorithms in Banach spaces
• Local entropy in learning theory
• On adaptive estimators in statistical learning theory
• A deterministic learning approach based on discrepancy.
• \(L^p\)-convergence of greedy algorithm by generalized Walsh system
• On the entropy numbers between the anisotropic spaces and the spaces of functions with mixed smoothness
• Integral norm discretization and related problems
• Sampling discretization and related problems
• A metric entropy bound is not sufficient for learnability
• Error Estimates for Multivariate Regression on Discretized Function Spaces
• Entropy numbers of functions on \([-1,1]\) with Jacobi weights
• Sampling discretization error of integral norms for function classes

This page was built for publication: The entropy in learning theory. Error estimates

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q854989)