A game-theoretic perspective of deep neural networks

DOI10.1016/J.TCS.2022.09.035MaRDI QIDQ2098170zbMATH OpenOpenAlexFDO

Authors Chunying Ren, Wen-Qing Xu, Zijun Wu, Dachuan Xu

Publication date 17 November 2022

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

Full work available at URL https://doi.org/10.1016/j.tcs.2022.09.035

zbMATH Keywords

deep neural networkslocal minimanon-atomic congestion gamewardrop equilibria

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Applications of game theory (91A80)

Recommendations

• A game-theoretic analysis of deep neural networks
• Nash equilibria in multineuron games
• Principled deep neural network training through linear programming
• Deep fictitious play for stochastic differential games
• Mean Field Analysis of Deep Neural Networks

Cites work

• 10.1162/1532443041827880
• An Introduction to Variational Inequalities and Their Applications
• Deep learning
• Generic uniqueness of equilibrium in large crowding games
• How bad is selfish routing?
• scientific article; zbMATH DE number 784362 (Why is no real title available?)
• Reducing the Dimensionality of Data with Neural Networks
• Selfishness need not be bad
• Some NP-complete problems in quadratic and nonlinear programming
• Worst-case equilibria

Cited in

(4)

• Differential neural networks for identification and filtering in nonlinear dynamic games
• A game-theoretic analysis of deep neural networks
• DEEP EQUILIBRIUM NETS
• A dynamical neural network approach for solving stochastic two-player zero-sum games

Describes a project that uses

Uses Software

• darch

This page was built for publication: A game-theoretic perspective of deep neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2098170)