Optimal convergence rate of the universal estimation error

DOI10.1186/S40687-016-0093-6MaRDI QIDQ516004zbMATH OpenOpenAlexWikidataFDO

Authors Yao Wang, Weinan E

Publication date 20 March 2017

Published in Research in the Mathematical Sciences (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.1186/s40687-016-0093-6

zbMATH Keywords

optimal convergenceminimax optimal rateuniversal estimation error

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Asymptotic properties of nonparametric inference (62G20) Ridge regression; shrinkage estimators (Lasso) (62J07) Inequalities; stochastic orderings (60E15)

Recommendations

• scientific article; zbMATH DE number 67635
• Lower Bounds for the Empirical Minimization Algorithm
• Minimax nonparametric classification .I. Rates of convergence
• The convergence rate of learning algorithms for least square regression with sample dependent hypothesis spaces
• Optimal global rates of convergence for noiseless regression estimation problems with adaptively chosen design

Cites work

• scientific article; zbMATH DE number 194093 (Why is no real title available?)
• scientific article; zbMATH DE number 194266 (Why is no real title available?)
• 10.1162/153244302760200713
• 10.1162/153244303321897690
• Boosting the margin: a new explanation for the effectiveness of voting methods
• Covering numbers for real-valued function classes
• Introduction to empirical processes and semiparametric inference
• Local Rademacher complexities
• Necessary and Sufficient Conditions for the Uniform Convergence of Means to their Expectations
• Rademacher averages and phase transitions in Glivenko-Cantelli classes
• Scale-sensitive dimensions, uniform convergence, and learnability
• Some limit theorems for empirical processes (with discussion)
• The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the network
• Uniform and universal Glivenko-Cantelli classes
• epsilon-entropy of convex sets and functions

Cited in

(3)

• scientific article; zbMATH DE number 5258492 (Why is no real title available?)
• The taut string approach to statistical inverse problems: theory and applications
• An improved uniform convergence bound with fat-shattering dimension

This page was built for publication: Optimal convergence rate of the universal estimation error

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q516004)