Conditional Density Estimation, Latent Variable Discovery and Optimal Transport

Abstract

A framework is proposed that addresses both conditional density estimation and latent variable discovery. The objective function maximizes explanation of variability in the data, achieved through the optimal transport barycenter generalized to a collection of conditional distributions indexed by a covariate --either given or latent-- in any suitable space. Theoretical results establish the existence of barycenters, a minimax formulation of optimal transport maps, and a general characterization of variability via the optimal transport cost. This framework leads to a family of non-parametric neural network-based algorithms, the BaryNet, with a supervised version that estimates conditional distributions and an unsupervised version that assigns latent variables. The efficacy of BaryNets is demonstrated by tests on both artificial and real-world data sets. A parallel drawn between autoencoders and the barycenter framework leads to the Barycentric autoencoder algorithm (BAE).

References in corpus (9)

• Conditional Generative Adversarial Nets
• Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networks
• On Gradient Descent Ascent for Nonconvex-Concave Minimax Problems
• Gradient Descent with Early Stopping is Provably Robust to Label Noise for Overparameterized Neural Networks
• A Priori Estimates of the Population Risk for Two-layer Neural Networks
• Conditional Density Estimation with Bayesian Normalising Flows
• Fast Nonparametric Conditional Density Estimation
• Clustering, factor discovery and optimal transport
• An implicit gradient-descent procedure for minimax problems

Cited by in corpus (2)

• Clustering, factor discovery and optimal transport
• Density Estimation via Measure Transport: Outlook for Applications in the Biological Sciences