Mathematical Theory of Robustness of Neural Networks
Event details
| Date | 07.02.2023 |
| Hour | 10:15 › 12:15 |
| Speaker | Thomas Weinberger |
| Category | Conferences - Seminars |
EDIC candidacy exam
Exam president: Prof.Nicolas Flammarion
Thesis advisor: Prof. Rüdiger Urbanke
Co-examiner: Prof. Lenaic Chizat
Abstract
coming soon
Background papers
Gradient Methods Provably Converge to Non-Robust Networks
A single gradient step finds adversarial examples on random two-layers neural networks
Adversarially Robust Generalization Requires More Data
Exam president: Prof.Nicolas Flammarion
Thesis advisor: Prof. Rüdiger Urbanke
Co-examiner: Prof. Lenaic Chizat
Abstract
coming soon
Background papers
Gradient Methods Provably Converge to Non-Robust Networks
A single gradient step finds adversarial examples on random two-layers neural networks
Adversarially Robust Generalization Requires More Data
Practical information
- General public
- Free
Contact
- edic@epfl.ch