Mirror Sinkhorn: Fast Online Optimization on Transport PolytopesDownload PDFOpen Website

12 Jan 2023OpenReview Archive Direct UploadReaders: Everyone
Abstract: Optimal transport has arisen as an important tool in machine learning, allowing to capture geometric properties of the data. It is formulated as a linear program on transport polytopes. The problem of convex optimization on this set includes both OT and multiple related ones, such as point cloud registration. We present in this work an optimization algorithm that utilizes Sinkhorn matrix scaling and mirror descent to minimize convex objectives on this domain. This algorithm can be run online and is both adaptive and robust to noise. A mathematical analysis of the convergence rate of the algorithm for minimising convex functions is provided, as well as experiments that illustrate its performance on synthetic data and real-world data.
0 Replies

Loading