A Compact Network Learning Model for Distribution Regression

TL;DR

This paper introduces a novel distribution regression network that encodes entire functions in single nodes, resulting in higher accuracy and more compact models compared to traditional neural networks.

Contribution

The paper proposes a new network architecture that encodes functions in single nodes, addressing the limitations of traditional neural networks in function space regression.

Findings

Achieves higher prediction accuracy than traditional models.

Uses fewer parameters, leading to more compact networks.

Demonstrates effectiveness on distribution regression tasks.

Abstract

Despite the superior performance of deep learning in many applications, challenges remain in the area of regression on function spaces. In particular, neural networks are unable to encode function inputs compactly as each node encodes just a real value. We propose a novel idea to address this shortcoming: to encode an entire function in a single network node. To that end, we design a compact network representation that encodes and propagates functions in single nodes for the distribution regression task. Our proposed Distribution Regression Network (DRN) achieves higher prediction accuracies while being much more compact and uses fewer parameters than traditional neural networks.