Deep linear neural networks with arbitrary loss: All local minima are global

Abstract

We consider deep linear networks with arbitrary convex differentiable loss. We provide a short and elementary proof of the fact that all local minima are global minima if the hidden layers are either 1) at least as wide as the input layer, or 2) at least as wide as the output layer. This result is the strongest possible in the following sense: If the loss is convex and Lipschitz but not differentiable then deep linear networks can have sub-optimal local minima.

Cited by in corpus (7)

• Learning ReLU Networks on Linearly Separable Data: Algorithm, Optimality, and Generalization
• The Multilinear Structure of ReLU Networks
• Pure and Spurious Critical Points: a Geometric Study of Linear Networks
• The Global Optimization Geometry of Shallow Linear Neural Networks
• Collective evolution of weights in wide neural networks
• On the Stability Properties and the Optimization Landscape of Training Problems with Squared Loss for Neural Networks and General Nonlinear Conic Approximation Schemes
• Adaptive Stochastic Gradient Langevin Dynamics: Taming Convergence and Saddle Point Escape Time