Progressively applying Gaussian noise transforms complex data distributions to approximately Gaussian. Reversing this dynamic defines a generative model. When the …
Solving transport problems, ie finding a map transporting one given distribution to another, has numerous applications in machine learning. Novel mass transport methods motivated …
Simulation-free methods for training continuous-time generative models construct probability paths that go between noise distributions and individual data samples. Recent works, such …
We analyze a number of natural estimators for the optimal transport map between two distributions and show that they are minimax optimal. We adopt the plugin approach: our …
AA Pooladian, V Divol… - … Conference on Machine …, 2023 - proceedings.mlr.press
We consider the problem of estimating the optimal transport map between two probability distributions, $ P $ and $ Q $ in $\mathbb {R}^ d $, on the basis of iid samples. All existing …
Flow-based models are powerful tools for designing probabilistic models with tractable density. This paper introduces Convex Potential Flows (CP-Flow), a natural and efficient …
B Dai, U Seljak - arXiv preprint arXiv:2007.00674, 2020 - arxiv.org
We develop an iterative (greedy) deep learning (DL) algorithm which is able to transform an arbitrary probability distribution function (PDF) into the target PDF. The model is based on …
We consider the problem of estimating the optimal transport map between a (fixed) source distribution $ P $ and an unknown target distribution $ Q $, based on samples from $ Q …
We investigate the optimal transport problem between probability measures when the underlying cost function is understood to satisfy a least action principle, also known as a …