The LCFI website uses cookies only for anonymised website statistics and for ensuring our security, never for tracking or identifying you individually. To find out more, and to find out how we protect your personal information, please read our privacy policy.

Learning with Hyperspherical Uniformity

Workshop Paper by Weiyang Liu, Rongmei Lin, Zhen Liu, Li Xiong, Bernhard Schölkopf , Adrian Weller

Learning with Hyperspherical Uniformity. 24th International Conference on Artificial Intelligence and Statistics - AISTATS 2021. https://arxiv.org/abs/2103.01649

Abstract: Due to the over-parameterization nature, neural networks are a powerful tool for nonlinear function approximation. In order to achieve good generalization on unseen data, a suitable inductive bias is of great importance for neural networks. One of the most straightforward ways is to regularize the neural network with some additional objectives. L2 regularization serves as a standard regularization for neural networks. Despite its popularity, it essentially regularizes one dimension of the individual neuron, which is not strong enough to control the capacity of highly over-parameterized neural networks. Motivated by this, hyperspherical uniformity is proposed as a novel family of relational regularizations that impact the interaction among neurons. We consider several geometrically distinct ways to achieve hyperspherical uniformity. The effectiveness of hyperspherical uniformity is justified by theoretical insights and empirical evaluations. 

Download Workshop Paper