Doctoral student in Optimal Transport for Optimization and Machine Learning

Project description

Third-cycle subject: Applied and computational mathematics

The project focuses on applying optimal transport and gradient flows to machine learning and optimization applications, such as deep generative models, sampling, inference, stochastic optimization, and beyond. The doctoral student will develop and analyze mathematical models and algorithms that connect partial (and/or stochastic) differential equations, infinite-dimensional optimization, and statistical machine learning. The goal is to build a theoretical and computational foundation for new methods in statistical inference and generative modeling, based on principled optimal transport and gradient flow theory.

We are looking for a highly motivated candidate with a strong background in mathematics, applied mathematics, or related fields, and with an interest in both theory and applications.

The doctoral student will be placed at the Department of Mathematics, S...