A Functional Perspective on Learning Symmetric Functions with Neural Networks

Abstract

Symmetric functions, which take as input an unordered, fixed-size set, are known to be universally representable by neural networks that enforce permutation invariance. These architectures only give guarantees for fixed input sizes, yet in many practical applications, including point clouds and particle physics, a relevant notion of generalization should include varying the input size. In this work we treat symmetric functions (of any size) as functions over probability measures, and study the learning and representation of neural networks defined on measures. By focusing on shallow architectures, we establish approximation and generalization bounds under different choices of regularization (such as RKHS and variation norms), that capture a hierarchy of functional spaces with increasing degree of non-linear learning. The resulting models can be learned efficiently and enjoy generalization guarantees that extend across input sizes, as we verify empirically.

Accepted to ICML 2021

References in corpus (6)

• In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learning
• Functional Multi-Layer Perceptron: a Nonlinear Tool for Functional Data Analysis
• Norm-Based Capacity Control in Neural Networks
• Approximation capability of neural networks on spaces of probability measures and tree-structured domains
• On Sparsity in Overparametrised Shallow ReLU Networks
• The Quenching-Activation Behavior of the Gradient Descent Dynamics for Two-layer Neural Network Models