Statistical Optimal Transport

Statistics and Data Science Center faculty member Philippe Rigollet is the co-author of the new book Statistical Optimal Transport, which gathers material on optimal transport central to applications in statistics and machine learning, and provides a unique overview of the current state of the field. The text, co-authored with Sinho Chewi and Jonathan Niles-Weed, includes in-depth mathematical treatment of novel questions arising in statistical optimal transport.

While the book is primarily tailored for students and researchers in these fields, the authors took care to make it accessible to a broader audience of applied mathematicians and computer scientists. Each chapter is complemented with exercises for the reader to test their understanding, making the text suitable for a graduate course on the topic.

Philippe Rigollet is the Cecil and Ida Green Distinguished Professor of Mathematics with additional affiliations in the Institute for Data, Systems, and Society (IDSS), the Laboratory for Information and Decision Systems (LIDS), and the Broad Institute. His research interests span a wide range of mathematical topics, particularly those emerging from the fields of statistics, data science, and artificial intelligence. In addition to statistical optimal transport, Rigollet focuses on the mathematical foundations of transformers, which play a central role in the inner workings of large language models. He and his group are also contributing to new research collaborations in biomedical science, investigators with machine learning and biomedical backgrounds from the Broad Institute, MIT, and Harvard to apply cutting-edge machine learning techniques to research focused on important challenges in biomedical science. joins efforts to map the cell intrinsic and extrinsic programs defining tissue zonation in the liver

For more information, downloads, and orders, visit the publisher’s page on Statistical Optimal Transport.