Paper ID: 2409.13672

Recent Advances in Non-convex Smoothness Conditions and Applicability to Deep Linear Neural Networks

Vivak Patel, Christian Varner

The presence of non-convexity in smooth optimization problems arising from deep learning have sparked new smoothness conditions in the literature and corresponding convergence analyses. We discuss these smoothness conditions, order them, provide conditions for determining whether they hold, and evaluate their applicability to training a deep linear neural network for binary classification.

Submitted: Sep 20, 2024