Characterization of Gradient Dominance and Regularity Conditions for Neural Networks
This work offers incremental theoretical insights into loss function landscapes for neural networks, benefiting researchers in optimization and deep learning theory.
The paper characterizes global minimizers and establishes gradient dominance and regularity conditions for the square loss of three neural network types, providing theoretical guarantees for optimization near these minimizers.
The past decade has witnessed a successful application of deep learning to solving many challenging problems in machine learning and artificial intelligence. However, the loss functions of deep neural networks (especially nonlinear networks) are still far from being well understood from a theoretical aspect. In this paper, we enrich the current understanding of the landscape of the square loss functions for three types of neural networks. Specifically, when the parameter matrices are square, we provide an explicit characterization of the global minimizers for linear networks, linear residual networks, and nonlinear networks with one hidden layer. Then, we establish two quadratic types of landscape properties for the square loss of these neural networks, i.e., the gradient dominance condition within the neighborhood of their full rank global minimizers, and the regularity condition along certain directions and within the neighborhood of their global minimizers. These two landscape properties are desirable for the optimization around the global minimizers of the loss function for these neural networks.