Generalization in Deep Learning

This chapter provides theoretical insights into why and how deep learning can generalize well, despite its large capacity, complexity, possible algorithmic instability, non-robustness, and sharp minima, responding to an open question in the literature. We also discuss approaches to provide non-vacuous generalization guarantees for deep learning. On the basis of the theoretical observations, we propose new open problems.

# Stochastic Gradient Optimization Techniques # Computer Science # Machine Learning and Algorithms # Domain Adaptation and Few-Shot Learning

Kenji Kawaguchi, Yoshua Bengio, Leslie Pack Kaelbling (2022). "Generalization in Deep Learning". Cambridge University Press eBooks. https://doi.org/10.1017/9781009025096.003