Learning towards Minimum Hyperspherical Energy

TL;DR

This paper introduces a novel regularization method called Minimum Hyperspherical Energy (MHE) for neural networks, inspired by physics, to reduce neuron redundancy and improve generalization, demonstrating superior performance in experiments.

Contribution

The paper proposes the MHE regularization technique for neural networks, inspired by the Thomson problem, with theoretical insights and multiple variants, showing improved results.

Findings

MHE effectively reduces neuron redundancy.

Neural networks with MHE outperform baselines.

MHE improves generalization in challenging tasks.

Abstract

Neural networks are a powerful class of nonlinear functions that can be trained end-to-end on various applications. While the over-parametrization nature in many neural networks renders the ability to fit complex functions and the strong representation power to handle challenging tasks, it also leads to highly correlated neurons that can hurt the generalization ability and incur unnecessary computation cost. As a result, how to regularize the network to avoid undesired representation redundancy becomes an important issue. To this end, we draw inspiration from a well-known problem in physics -- Thomson problem, where one seeks to find a state that distributes N electrons on a unit sphere as evenly as possible with minimum potential energy. In light of this intuition, we reduce the redundancy regularization problem to generic energy minimization, and propose a minimum hyperspherical energy (MHE) objective as generic regularization for neural networks. We also propose a few novel variants of MHE, and provide some insights from a theoretical point of view. Finally, we apply neural networks with MHE regularization to several challenging tasks. Extensive experiments demonstrate the effectiveness of our intuition, by showing the superior performance with MHE regularization.