A distributed framework for the construction of transport maps

DOI10.1162/NECO_A_01172MaRDI QIDQ5154132zbMATH OpenOpenAlexDBLPWikidataFDO

Authors Diego A. Mesa, Justin Tantiongloc, Marcela Mendoza, Sanggyun Kim, Todd Coleman

Publication date 1 October 2021

Published in Neural Computation (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1801.08454

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Transportation, logistics and supply chain management (90B06) Combinatorial optimization (90C27)

Abstract: The need to reason about uncertainty in large, complex, and multi-modal datasets has become increasingly common across modern scientific environments. The ability to transform samples from one distribution $P$ to another distribution $Q$ enables the solution to many problems in machine learning (e.g. Bayesian inference, generative modeling) and has been actively pursued from theoretical, computational, and application perspectives across the fields of information theory, computer science, and biology. Performing such transformations, in general, still leads to computational difficulties, especially in high dimensions. Here, we consider the problem of computing such "measure transport maps" with efficient and parallelizable methods. Under the mild assumptions that $P$ need not be known but can be sampled from, and that the density of $Q$ is known up to a proportionality constant, and that $Q$ is log-concave, we provide in this work a convex optimization problem pertaining to relative entropy minimization. We show how an empirical minimization formulation and polynomial chaos map parameterization can allow for learning a transport map between $P$ and $Q$ with distributed and scalable methods. We also leverage findings from nonequilibrium thermodynamics to represent the transport map as a composition of simpler maps, each of which is learned sequentially with a transport cost regularized version of the aforementioned problem formulation. We provide examples of our framework within the context of Bayesian inference for the Boston housing dataset and generative modeling for handwritten digit images from the MNIST dataset.

Recommendations

• Transport map accelerated Markov chain Monte Carlo
• Data-driven optimal transport
• Adaptive optimal transport
• Bayesian inference with optimal maps
• Inference via low-dimensional couplings

Cites work

• A multiscale strategy for Bayesian inference using transport maps
• An augmented Lagrangian approach to Wasserstein gradient flows and applications
• An introduction to MCMC for machine learning
• Bayesian data analysis.
• Bayesian inference with optimal maps
• Bayesian lasso regression
• Concentration of the information in data with log-concave distributions
• Coordinate descent algorithms
• Distributed optimization and statistical learning via the alternating direction method of multipliers
• Free energy and the Fokker-Planck equation
• From Knothe's Rearrangement to Brenier's Optimal Transport Map
• Hedonic housing prices and the demand for clean air
• scientific article; zbMATH DE number 4063438 (Why is no real title available?)
• scientific article; zbMATH DE number 1909499 (Why is no real title available?)
• scientific article; zbMATH DE number 2107836 (Why is no real title available?)
• scientific article; zbMATH DE number 2117879 (Why is no real title available?)
• scientific article; zbMATH DE number 3894218 (Why is no real title available?)
• scientific article; zbMATH DE number 5043156 (Why is no real title available?)
• Iterative Bregman projections for regularized transportation problems
• Log-concave probability and its applications
• Monte Carlo sampling methods using Markov chains and their applications
• Monte Carlo strategies in scientific computing.
• On the ``degrees of freedom of the lasso
• Optimal Transport
• Optimal transport for applied mathematicians. Calculus of variations, PDEs, and modeling
• Optimal transport with proximal splitting
• Scalable Bayes via barycenter in Wasserstein space
• Stochastic processes and orthogonal polynomials
• Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images
• The Bayesian Lasso
• The Variational Formulation of the Fokker--Planck Equation
• Transport map accelerated Markov chain Monte Carlo

Cited in

(5)

• Deep composition of tensor-trains using squared inverse Rosenblatt transports
• Transport map accelerated Markov chain Monte Carlo
• Inference via low-dimensional couplings
• Scalable conditional deep inverse Rosenblatt transports using tensor trains and gradient-based dimension reduction
• On the representation and learning of monotone triangular transport maps

Describes a project that uses

Uses Software

• Wasserstein GAN
• BayesDA

This page was built for publication: A distributed framework for the construction of transport maps

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5154132)