Compelling ReLU Networks to Exhibit Exponentially Many Linear Regions at Initialization and During Training

Max Milkert; David Hyde; Forrest John Laine

2025 ICML ICML 2025

Compelling ReLU Networks to Exhibit Exponentially Many Linear Regions at Initialization and During Training

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Max Milkert, David Hyde, Forrest John Laine

Topics

Machine Learning > Optimization & Theory > Learning Theory Deep Learning > Architectures > Neural Networks Deep Learning > Techniques > Model Architecture

Keywords

convex function linear region relu non-convex parameterization multi-dimensional

Download PDF