A Compact Network Learning Model for Distribution Regression
arXiv:1804.04775
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.
References in corpus (7)
- Density estimation using Real NVP
- Tensorizing Neural Networks
- Equilibrium Distribution of Heavy Quarks in Fokker-Planck Dynamics
- Stochastic Analysis and Regeneration of Rough Surfaces
- The Ornstein-Uhlenbeck process with migration: evolution with interactions
- Grid-free powder averages: on the applications of the Fokker-Planck equation to solid state NMR
- Understanding the 2016 US Presidential Election using ecological inference and distribution regression with census microdata