Embedding Principle of Loss Landscape of Deep Neural Networks

Abstract

Understanding the structure of loss landscape of deep neural networks (DNNs)is obviously important. In this work, we prove an embedding principle that the loss landscape of a DNN "contains" all the critical points of all the narrower DNNs. More precisely, we propose a critical embedding such that any critical point, e.g., local or global minima, of a narrower DNN can be embedded to a critical point/hyperplane of the target DNN with higher degeneracy and preserving the DNN output function. The embedding structure of critical points is independent of loss function and training data, showing a stark difference from other nonconvex problems such as protein-folding. Empirically, we find that a wide DNN is often attracted by highly-degenerate critical points that are embedded from narrow DNNs. The embedding principle provides an explanation for the general easy optimization of wide DNNs and unravels a potential implicit low-complexity regularization during the training. Overall, our work provides a skeleton for the study of loss landscape of DNNs and its implication, by which a more exact and comprehensive understanding can be anticipated in the near

References in corpus (6)

• On Exact Computation with an Infinitely Wide Neural Net
• A Closer Look at Memorization in Deep Networks
• Stochastic Gradient Descent Optimizes Over-parameterized Deep ReLU Networks
• A Comparative Analysis of the Optimization and Generalization Property of Two-layer Neural Network and Random Feature Models Under Gradient Descent Dynamics
• Towards a Mathematical Understanding of Neural Network-Based Machine Learning: what we know and what we don't
• Asymmetric Valleys: Beyond Sharp and Flat Local Minima