Research interests

My research background is in optimal transport: the mathematics of moving one distribution of mass onto another as cheaply as possible. It turns out to be a very natural way to measure how far apart two probability distributions are, which is why it shows up across machine learning, statistics and economics.

I work on its algorithmic side, and in particular on making it usable on real data. Classical optimal transport struggles when the data has many dimensions, and it is easily thrown off by noise and outliers. A lot of my work adds structure to the problem, through low-dimensional projections, convexity and regularity, so that optimal transport stays reliable and fast to compute. I have used these ideas in machine learning and in economics.

I am now a Member of Technical Staff at The Forecasting Company, which builds foundation models for time-series forecasting. Previously, at Ida, I worked on forecasting and operations research for fresh-food ordering, bringing models and optimization algorithms into production.

See my work come to life in interactive demos →

Publications

Talks & tutorials