Self-improved gaps almost everywhere for the agnostic approximation of monomials

DOI10.1016/J.TCS.2007.02.023zbMATH Open1117.68040OpenAlexW2135781605MaRDI QIDQ884469FDOQ884469

Authors: Richard Nock, Frank Nielsen 

Publication date: 6 June 2007

Published in: Theoretical Computer Science (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.tcs.2007.02.023

Recommendations

• On the difficulty of approximately maximizing agreements.
• On agnostic learning of parities, monomials, and halfspaces
• Lower bounds for agnostic learning via approximate rank
• scientific article; zbMATH DE number 2089368

zbMATH Keywords

monomialsagnostic learningself-improving reductions

Mathematics Subject Classification ID

Computational learning theory (68Q32)

Cites Work

• A decision-theoretic generalization of on-line learning and an application to boosting
• Additive logistic regression: a statistical view of boosting. (With discussion and a rejoinder by the authors)
• Very simple classification rules perform well on most commonly used datasets
• Improved boosting algorithms using confidence-rated predictions
• Title not available (Why is that?)
• Clique is hard to approximate within \(n^{1-\epsilon}\)
• Linear degree extractors and the inapproximability of max clique and chromatic number
• Title not available (Why is that?)
• Toward efficient agnostic learning
• Robust trainability of single neurons
• On the limits of proper learnability of subclasses of DNF formulas
• Lower bounds on learning decision lists and trees
• Maximizing agreements and coagnostic learning
• Complexity in the case against accuracy estimation
• Title not available (Why is that?)
• Title not available (Why is that?)

Uses Software

• AdaBoost.MH

This page was built for publication: Self-improved gaps almost everywhere for the agnostic approximation of monomials

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q884469)