Nonexact oracle inequalities, \(r\)-learnability, and fast rates

DOI10.1016/j.jco.2023.101804OpenAlexW4387618800MaRDI QIDQ6149162

Daniel Z. Zanger

Publication date: 5 February 2024

Published in: Journal of Complexity (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.jco.2023.101804

zbMATH Keywords

agnostic learningempirical risk minimizationsample complexityfast learning ratesnonexact oracle inequalities

Mathematics Subject Classification ID

Linear regression; mixed models (62J05) Statistical methods; risk measures (91G70) Analysis of algorithms and problem complexity (68Q25) Learning and adaptive systems in artificial intelligence (68T05) Complexity and performance of numerical algorithms (65Y20)

Cites Work

• General nonexact oracle inequalities for classes with a subexponential envelope
• Monte Carlo algorithms for optimal stopping and statistical learning
• Risk bounds for statistical learning
• Sphere packing numbers for subsets of the Boolean \(n\)-cube with bounded Vapnik-Chervonenkis dimension
• Distribution-free robust linear regression
• Nonparametric regression using deep neural networks with ReLU activation function
• On the mathematical foundations of learning
• General Error Estimates for the Longstaff–Schwartz Least-Squares Monte Carlo Algorithm
• Efficient agnostic learning of neural networks with bounded fan-in
• CONVERGENCE OF A LEAST‐SQUARES MONTE CARLO ALGORITHM FOR AMERICAN OPTION PRICING WITH DEPENDENT SAMPLE DATA
• The importance of convexity in learning with squared loss
• Convergence of stochastic processes
• Unnamed Item
• Unnamed Item

This page was built for publication: Nonexact oracle inequalities, \(r\)-learnability, and fast rates