Jonathan Niles-Weed

Jonathan Niles-Weed is an Associate Professor of Mathematics and Data Science at the Courant Institute of Mathematical Sciences and the Center for Data Science at New York University. He is a core member of the Math and Data and STAT groups. His research focuses on statistics, probability, and the mathematics of data science, particularly statistical and computational problems arising from data with geometric structure. His recent work includes developing a statistical theory of optimal transport. Niles-Weed received his Ph.D. in Mathematics and Statistics from MIT under the supervision of Philippe Rigollet. His research is supported by the National Science Foundation, Google Research, and an Alfred P. Sloan Foundation fellowship. He co-authored a monograph on Statistical Optimal Transport with Sinho Chewi and Philippe Rigollet.

Jonathan Niles-Weed is a researcher whose work focuses on statistics, probability, mathematics of data science, and optimal transport. His research explores the theoretical foundations of data science, with an emphasis on statistical methods for learning and inference. He has contributed to the development of algorithms for optimal transport, including Sinkhorn iteration and Nyström methods, which enable efficient computation of transport distances. His work also addresses the statistical properties of empirical measures in Wasserstein distances and the convergence of estimation methods in high-dimensional settings. Niles-Weed's research bridges theoretical statistics with practical data science problems, particularly in the areas of regularization, estimation, and learning under uncertainty.