Skip to content

Opening book details…

Can I read A Distributed Framework for the Construction of Transport Maps on EtoBox?

A Distributed Framework for the Construction of Transport Maps by Mesa, Diego A.; Tantiongloc, Justin; Mendoza, Marcela; Coleman, Todd P. is a scholarly article available to read on EtoBox.

What is A Distributed Framework for the Construction of Transport Maps about?

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

Author
Mesa, Diego A.; Tantiongloc, Justin; Mendoza, Marcela; Coleman, Todd P.
Published
2018
Language
EN

More by Mesa, Diego A.; Tantiongloc, Justin; Mendoza, Marcela; Coleman, Todd P.

Browse all works by Mesa, Diego A.; Tantiongloc, Justin; Mendoza, Marcela; Coleman, Todd P.