DC-programming for neural network optimizations

We discuss two key problems related to learning and optimization of neural networks: the computation of the adversarial attack for adversarial robustness and approximate optimization of complex functions. We show that both problems can be cast as instances of DC-programming. We give an explicit deco...

Full description

Saved in:
Bibliographic Details
Published inJournal of global optimization
Main Authors Awasthi, Pranjal, Mao, Anqi, Mohri, Mehryar, Zhong, Yutao
Format Journal Article
LanguageEnglish
Published 02.01.2024
Online AccessGet full text

Cover

More Information
Summary:We discuss two key problems related to learning and optimization of neural networks: the computation of the adversarial attack for adversarial robustness and approximate optimization of complex functions. We show that both problems can be cast as instances of DC-programming. We give an explicit decomposition of the corresponding functions as differences of convex functions (DC) and report the results of experiments demonstrating the effectiveness of the DCA algorithm applied to these problems.
ISSN:0925-5001
1573-2916
DOI:10.1007/s10898-023-01344-2