Gradient descent provably escapes saddle points in the training of shallow ReLU networks

Abstract

Dynamical systems theory has recently been applied in optimization to prove that gradient descent algorithms bypass so-called strict saddle points of the loss function. However, in many modern machine learning applications, the required regularity conditions are not satisfied. In this paper, we prove a variant of the relevant dynamical systems result, a center-stable manifold theorem, in which we relax some of the regularity requirements. We explore its relevance for various machine learning tasks, with a particular focus on shallow rectified linear unit (ReLU) and leaky ReLU networks with scalar input. Building on a detailed examination of critical points of the square integral loss function for shallow ReLU and leaky ReLU networks relative to an affine target function, we show that gradient descent circumvents most saddle points. Furthermore, we prove convergence to global minima under favourable initialization conditions, quantified by an explicit threshold on the limiting loss.

References in corpus (6)

• Complete Dictionary Recovery over the Sphere I: Overview and the Geometric Picture
• A Geometric Analysis of Phase Retrieval
• Splitting methods with variable metric for KL functions
• A Comparative Analysis of the Optimization and Generalization Property of Two-layer Neural Network and Random Feature Models Under Gradient Descent Dynamics
• A proof of convergence for gradient descent in the training of artificial neural networks for constant target functions
• Landscape analysis for shallow neural networks: complete classification of critical points for affine target functions

Cited by in corpus (1)

• Endogenous Regime Switching Driven by Scalar-Irreducible Learning Dynamics