Distribution Regression Network

by   Connie Kou, et al.
National University of Singapore
Agency for Science, Technology and Research

We introduce our Distribution Regression Network (DRN) which performs regression from input probability distributions to output probability distributions. Compared to existing methods, DRN learns with fewer model parameters and easily extends to multiple input and multiple output distributions. On synthetic and real-world datasets, DRN performs similarly or better than the state-of-the-art. Furthermore, DRN generalizes the conventional multilayer perceptron (MLP). In the framework of MLP, each node encodes a real number, whereas in DRN, each node encodes a probability distribution.


page 1

page 2

page 3

page 4


Multiple-Output Channel Simulation and Lossy Compression of Probability Distributions

We consider a variant of the channel simulation problem with a single in...

An Efficient Network for Predicting Time-Varying Distributions

While deep neural networks have achieved groundbreaking prediction resul...

Evaluating Bayes Error Estimators on Read-World Datasets with FeeBee

The Bayes error rate (BER) is a fundamental concept in machine learning ...

Synthesis of Stochastic Flow Networks

A stochastic flow network is a directed graph with incoming edges (input...

Factorization of Discrete Probability Distributions

We formulate necessary and sufficient conditions for an arbitrary discre...

Probabilistic 3d regression with projected huber distribution

Estimating probability distributions which describe where an object is l...

Probabilistic orientation estimation with matrix Fisher distributions

This paper focuses on estimating probability distributions over the set ...

Please sign up or login with your details

Forgot password? Click here to reset