Revisiting Landscape Analysis in Deep Neural Networks: Eliminating Decreasing Paths to Infinity

Abstract

Traditional landscape analysis of deep neural networks aims to show that no sub-optimal local minima exist in some appropriate sense. From this, one may be tempted to conclude that descent algorithms which escape saddle points will reach a good local minimum. However, basic optimization theory tell us that it is also possible for a descent algorithm to diverge to infinity if there are paths leading to infinity, along which the loss function decreases. It is not clear whether for non-linear neural networks there exists one setting that no bad local-min and no decreasing paths to infinity can be simultaneously achieved. In this paper, we give the first positive answer to this question. More specifically, for a large class of over-parameterized deep neural networks with appropriate regularizers, the loss function has no bad local minima and no decreasing paths to infinity. The key mathematical trick is to show that the set of regularizers which may be undesirable can be viewed as the image of a Lipschitz continuous mapping from a lower-dimensional Euclidean space to a higher-dimensional Euclidean space, and thus has zero measure.

References in corpus (6)

• The Loss Surfaces of Multilayer Networks
• Stochastic Gradient Descent Optimizes Over-parameterized Deep ReLU Networks
• Learning One-hidden-layer Neural Networks with Landscape Design
• Towards moderate overparameterization: global convergence guarantees for training shallow neural networks
• Globally Optimal Gradient Descent for a ConvNet with Gaussian Inputs
• Porcupine Neural Networks: (Almost) All Local Optima are Global

Cited by in corpus (1)

• Achieving Small Test Error in Mildly Overparameterized Neural Networks