Learning Theory of Distribution Regression with Neural Networks

TL;DR

This paper develops a theoretical framework for using neural networks to perform distribution regression, where inputs are probability measures, establishing approximation capabilities and learning rates.

Contribution

It introduces a novel neural network structure for distribution inputs and provides the first mathematical analysis of its approximation and learning properties.

Findings

Established a neural network framework for distribution regression.

Proved almost optimal learning rates for the proposed model.

Provided a two-stage error decomposition technique for analysis.

Abstract

In this paper, we aim at establishing an approximation theory and a learning theory of distribution regression via a fully connected neural network (FNN). In contrast to the classical regression methods, the input variables of distribution regression are probability measures. Then we often need to perform a second-stage sampling process to approximate the actual information of the distribution. On the other hand, the classical neural network structure requires the input variable to be a vector. When the input samples are probability distributions, the traditional deep neural network method cannot be directly used and the difficulty arises for distribution regression. A well-defined neural network structure for distribution inputs is intensively desirable. There is no mathematical model and theoretical analysis on neural network realization of distribution regression. To overcome technical difficulties and address this issue, we establish a novel fully connected neural network framework to realize an approximation theory of functionals defined on the space of Borel probability measures. Furthermore, based on the established functional approximation results, in the hypothesis space induced by the novel FNN structure with distribution inputs, almost optimal learning rates for the proposed distribution regression model up to logarithmic terms are derived via a novel two-stage error decomposition technique.