Recent Advances in Non-convex Smoothness Conditions and Applicability to Deep Linear Neural Networks
Machine Learning
2024-09-23 v1 Optimization and Control
Abstract
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.
Keywords
Cite
@article{arxiv.2409.13672,
title = {Recent Advances in Non-convex Smoothness Conditions and Applicability to Deep Linear Neural Networks},
author = {Vivak Patel and Christian Varner},
journal= {arXiv preprint arXiv:2409.13672},
year = {2024}
}