Pacific Interdisciplinary hub on Optimal Transport

2021 2024

The Pacific Interdisciplinary hub on Optimal Transport (PIHOT) is a Collaborative Research Group examining the research and applications of Optimal Transportation across a wide audience of researchers, students, industry, policy makers and the general public. 

 

The Kantorovich Initiative is a dedicated website to help foster a community around the topic of Optimal Transportation.

Scientific, Seminar
Kantorovich Initiative Seminar: Yousef Mroueh
December 13, 2024
University of British Columbia
Current LLM alignment techniques use pairwise human preferences at a sample level, and as such, they do not imply an alignment on the distributional level. We propose in this paper Alignment via Optimal Transport (AOT), a novel method for...
Scientific, Seminar
Kantorovich Initiative Seminar: Jia-Jie Zhu
December 16, 2024
University of British Columbia
Gradient flows have emerged as a powerful framework for analyzing machine learning and statistical inference algorithms. Motivated by several applications in statistical inference, generative models, generalization, and robustness of learning...
Scientific, Seminar
Kantorovich Initiative Seminar: Hugo Lavenant
November 21, 2024
University of British Columbia
The quadratically regularized optimal transport problem (QOT) has emerged in the literature as a sparse alternative to entropic regularization (EOT). Unlike EOT, whose solutions always have full support—even for small regularization parameters—QOT...
Scientific, Seminar
Kantorovich Initiative Seminar: Hugo Lavenant
October 31, 2024
University of British Columbia
What happens to Wasserstein gradient flows if one uses entropic optimal transport instead of classical optimal transport? I will explain why it may be relevant to use Sinkhorn divergences, built on entropic optimal transport, as they allow the...
Seminar
Kantorovich Initiative Seminar: Marco Cuturi
December 9, 2024
University of British Columbia
I will introduce our recent work on parameterising OT problems with elastic costs, i.e. ground costs that mix the classic squared Euclidean distance with a regularizer (e.g. L1 norm). After highlighting the properties of OT maps that follow such...
Scientific, Seminar
Kantorovich Initiative Seminar: Robert McCann
July 23, 2024
University of British Columbia
While Einstein’s theory of gravity is formulated in a smooth setting, the celebrated singularity theorems of Hawking and Penrose describe many physical situations in which this smoothness must eventually breakdown. In positive-definite signature...
Scientific, Seminar
Kantorovich Initiative Seminar: Laetitia Chapel
May 23, 2024
University of Washington
Optimal transport operates on empirical distributions which may contain acquisition artifacts, such as outliers or noise, thereby hindering a robust calculation of the OT map. Additionally, it necessitates equal mass between the two distributions...
Scientific, Seminar
Kantorovich Initiative Seminar: Yair Shenfeld
April 4, 2024
Online
Density functional theory (DFT) is one of the workhorses of quantum chemistry and material science. In principle, the joint probability of finding a specific electron configuration in a material is governed by a Schrödinger wave equation. But...
Scientific, Seminar
Kantorovich Initiative Seminar: Ziv Goldfeld
February 8, 2024
Online
The Gromov-Wasserstein (GW) distance quantifies dissimilarity between metric measure (mm) spaces and provides a natural alignment between them. As such, it serves as a figure of merit for applications involving alignment of heterogeneous datasets...
Scientific, Seminar
Kantorovich Initiative Seminar: Giuseppe Savare
November 30, 2023
I will try to present an overview of some results of unbalanced optimal transport for positive measures with different total masses, showing the crucial role of the so-called cone representation and of the corresponding homogeneous marginals. The...
Scientific, Seminar
Kantorovich Initiative Seminar: Jason Altschuler
October 12, 2023
Shifted divergences provide a principled way of making information theoretic divergences (e.g. KL) geometrically aware via optimal transport smoothing. In this talk, I will argue that shifted divergences provide a powerful approach towards unifying...
Professor of Mathematics, University of Washington
Professor of Mathematics, University of British Columbia
Associate Professor of Mathematics, University of Alberta