Excess risk bound for deep learning under weak dependence

DOI10.1002/MMA.10719MaRDI QIDQ6954102zbMATH OpenFDO

Authors William Charky Kengne

Publication date 24 July 2025

Published in Mathematical Methods in the Applied Sciences (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1002/MMA.10719

zbMATH Keywords

deep neural networksERM principleexcess riskfunction approximationweak dependence

Mathematics Subject Classification ID

General and overarching topics; collections (00-XX)

Cites work

• A general procedure for change-point detection in multivariate time series
• A new weak dependence condition and applications to moment inequalities
• A study on moment inequalities under a weak dependence
• Error bounds for approximations with deep ReLU networks
• Fast convergence rates of deep neural networks for classification
• scientific article; zbMATH DE number 53328 (Why is no real title available?)
• Inference and model selection in general causal time series with exogenous covariates
• Nonconvex Sparse Regularization for Deep Neural Networks and Its Optimality
• Nonparametric regression using deep neural networks with ReLU activation function
• On deep learning as a remedy for the curse of dimensionality in nonparametric regression
• Optimal approximation of piecewise smooth functions using deep ReLU neural networks
• QML inference for volatility models with covariates
• Theory and practice of finite elements.
• Weak dependence. With examples and applications.

Cited in

(2)

• Minimax optimality of deep neural networks on dependent data via PAC-Bayes bounds
• Deep learning from strongly mixing observations: sparse-penalized regularization and minimax optimality

This page was built for publication: Excess risk bound for deep learning under weak dependence

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6954102)