Formalizing Generalization and Robustness of Neural Networks to Weight Perturbations

Yu-Lin Tsai, Chia-Yi Hsu, Chia-Mu Yu, Pin-Yu Chen

Keywords: Generalization, Robustness, Neural Network, Weight Perturbation, Rademacher complexity

Abstract: Studying the sensitivity of weight perturbation in neural networks and its impacts on model performance, including generalization and robustness, is an active research topic due to its implications on a wide range of machine learning tasks such as model compression, generalization gap assessment, and adversarial attacks. In this paper, we provide the first formal analysis for feed-forward neural networks with non-negative monotone activation functions against norm-bounded weight perturbations, in terms of the robustness in pairwise class margin functions and the Rademacher complexity for generalization. We further design a new theory-driven loss function for training generalizable and robust neural networks against weight perturbations. Empirical experiments are conducted to validate our theoretical analysis. Our results offer fundamental insights for characterizing the generalization and robustness of neural networks against weight perturbations.

One-sentence Summary: We provide a comprehensive theoretical analysis on the generalization and robustness of neural networks against weight perturbations, and propose a new theory-driven training loss

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=Q9Oz-cSkP7