Phase diagram for two-layer ReLU neural networks at infinite-width limit

Abstract

How neural network behaves during the training over different choices of hyperparameters is an important question in the study of neural networks. In this work, inspired by the phase diagram in statistical mechanics, we draw the phase diagram for the two-layer ReLU neural network at the infinite-width limit for a complete characterization of its dynamical regimes and their dependence on hyperparameters related to initialization. Through both experimental and theoretical approaches, we identify three regimes in the phase diagram, i.e., linear regime, critical regime and condensed regime, based on the relative change of input weights as the width approaches infinity, which tends to $0$, $O(1)$ and $+\infty$, respectively. In the linear regime, NN training dynamics is approximately linear similar to a random feature model with an exponential loss decay. In the condensed regime, we demonstrate through experiments that active neurons are condensed at several discrete orientations. The critical regime serves as the boundary between above two regimes, which exhibits an intermediate nonlinear behavior with the mean-field model as a typical example. Overall, our phase diagram for the two-layer ReLU NN serves as a map for the future studies and is a first step towards a more systematical investigation of the training behavior and the implicit regularization of NNs of different structures.

References in corpus (7)

• Neural Tangent Kernel: Convergence and Generalization in Neural Networks
• A Mean Field View of the Landscape of Two-Layers Neural Networks
• On Exact Computation with an Infinitely Wide Neural Net
• A Comparative Analysis of the Optimization and Generalization Property of Two-layer Neural Network and Random Feature Models Under Gradient Descent Dynamics
• Gradient Dynamics of Shallow Univariate ReLU Networks
• Gradient Descent Quantizes ReLU Network Features
• The Quenching-Activation Behavior of the Gradient Descent Dynamics for Two-layer Neural Network Models

Cited by in corpus (4)

• Modeling Structured Data Learning with Restricted Boltzmann Machines in the Teacher-Student Setting
• Deep frequency principle towards understanding why deeper learning is faster
• Phase Diagram of Initial Condensation for Two-layer Neural Networks
• An Upper Limit of Decaying Rate with Respect to Frequency in Deep Neural Network