Abstract
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.
Original language | English (US) |
---|---|
Journal | Journal of Global Optimization |
DOIs | |
State | Accepted/In press - 2024 |
Keywords
- Adversarial robustness
- DC-programming
- Function approximation
- Neural networks
- Optimization
ASJC Scopus subject areas
- Business, Management and Accounting (miscellaneous)
- Computer Science Applications
- Control and Optimization
- Management Science and Operations Research
- Applied Mathematics