Conveners
HDI Lab: Computational and statistical optimal transport 4
- Pavel Dvurechensky (WIAS Berlin)
HDI Lab: Computational and statistical optimal transport 3
- Pavel Dvurechensky (WIAS Berlin)
HDI Lab: Optimization methods for optimal transport 1
- Pavel Dvurechensky (WIAS Berlin)
HDI Lab: Optimization methods for optimal transport 2
- Pavel Dvurechensky (WIAS Berlin)
Description
In this lecture I will give a short introduction to optimal transport problem with some motivating examples from modern machine learning, including image retrieval and classification. The effectiveness of optimal transport in applications comes with the price of heavy computations and I will discuss two types of methods which allow to efficiently compute optimal transport distance (Wasserstein distance). The first method is Sinkhorn's algorithm and the second one is accelerated gradient method. If time allows I will also discuss a next level problem of finding Wasserstein barycenter of a set of measures, which works quite well in image analysis. Numerical methods for this problem will be discussed.
