Philippe Rigollet

Philippe Rigollet is the Cecil and Ida Green Distinguished Professor of Mathematics. His research interests span a wide range of mathematical topics, particularly those emerging from the fields of statistics, data science, and artificial intelligence. Currently, he focuses on statistical optimal transport and the mathematical foundations of Transformers.

Affiliations

Mathematics
IDSS
LIDS
Broad Institute
Philippe Rigollet

Academic Positions

Professor

MIT, Mathematics, 2020 -

Associate Professor

MIT, Mathematics, 2016 - 20

Assistant Professor

MIT, Mathematics, 2015 - 16

Assistant Professor

Princeton, ORFE, 2008 - 14

Postdoc

Georgia Tech, Mathematics, 2007 - 08

Education & Training

Ph.D. in Mathematics

Univ. of Paris 6 (now Sorbonne Univ.) - 2006

M. Sc. in Statistics & Actuarial Science

ISUP - 2003

B. Sc. in Applied Mathematics

Univ. of Paris 6 (now Sorbonne Univ.) - 2002

Selected Awards

Invited Speaker. International Congress of Mathematicians

2026

Invited speaker at ICM 2026 in Section 17: Statistics, Machine Learning, Image and Signal Processing.
Frank E. Perkins Award

2023

The Frank E. Perkins Award for Excellence in Graduate Advising is given each year to a professor from each school who has served as an excellent advisor and mentor for graduate students. The award is named in honor of Frank E. Perkins, Dean of the Graduate School from 1983-95.
Medallion lecture. Joint Statistical Meetings.

2021

Lecture on "Statistical Optimal Transport". Watch video here .
Elected IMS Fellow.

2021

For outstanding contributions to the analysis of statistical versus computational trade-offs, to the theory of aggregation, and to statistical optimal transport.
Best Paper Award.

2013

Berthet and Rigollet received "best paper award" at the Conference On Learning Theory (COLT) for their paper "Complexity Theoretic Lower Bounds for Sparse Principal Component Detection". In this work, they show that employing computationally efficient statistical methods in the context of sparse principal component analysis leads to an ineluctable deterioration of statistical performance, regardless of the efficient method employed. In particular, their paper draw new connections between statistical learning and computational complexity. An extended version of the paper is available here.
NSF CAREER Award.

2011

Large Scale Stochastic Optimization and Statistics..

Featured Work

..

Transformers and Self-Attention dynamics

ArXiv [2512.01868][2312.10794]

Our group recently initiated a line of work where we aim to develop a mathematical perspective on transformers by viewing them as interacting particle systems. As in neuralODEs, we view (self-attention) as velocity fields that evolve particles (token) towards a useful embedding. Our initial work has largely focused on shedding light on the clustering behavior of this system of interacting particles. Even in a very stylized model, many intriguiging mathematical questions arise.

..

Wasserstein gradient flows

YouTube EBA0NyY4Myc

This talk gives an overview of our recent work on applications of Wasserstein gradient flows to problems arising in statistics and machine learning. The Wasserstein geometry and its extensions (notably Wasserstein-Fisher-Rao) provide a toolbox to develop particle-based optimization algorithms over probability measures. These ideas have been implememented in several examples such as variational inference and nonparametric maximum likelihood estimation.

Measure-to-measure transformer regression

Biological applications

ArXiv 2605.28075

Our group is applying transformers to biological data by treating entire cell populations as probability measures. This measure-to-measure perspective learns how distributions evolve under interventions, using transformers as static maps or dynamic velocity fields to predict treatment response in settings such as patient-derived organoids.

Research Group

Andrew Yao

Andrew Yao

Ph.D Student
Emre Parmaksiz

Emre Parmaksiz

Ph.D Student
Kaizhao Liu

Kaizhao Liu

Ph.D Student
Mara

Mara Daniels

Ph.D Student
Mohammad

Mohammad Reza Karimi

C.L.E Moore Instructor
Omar

Omar Al-Ghattas

NSF Postdoc
Shi

Shi Chen

C.L.E Moore Instructor
Zhengjiang

Zhengjiang Lin

C.L.E Moore Instructor

Alumni

Aleksandr Zimin, Postdoc at Broad Institute
2026
Enric Boix, Assistant Prof. at UPenn
2024
George Stepaniants, Assistant Prof. at Cambridge U.
2024
Patrik Gerber, Quant at Citadel
2024
Felipe Suarez, Quant at DRW
2023
Sinho Chewi, Assistant Prof. at Yale
2023
Austin Stromme, Assistant Prof. at ENSAE
2023
Chen Lu, Member of tech. staff at Cursor
2023
Julien Clancy, Quant at Citadel
2021
Paxton Turner, AI Scientist at Arbol
2021
Jan-Christian Hütter, Principal ML Scientist at Genenetech
2019
Jonathan Niles-Weed, Associate Prof. at NYU
2019
Cheng Mao, Assistant Prof. at Georgia Tech
2018
Lucy Xia, Assistant Prof. at HKUST
2015
Quentin Berthet, Research Scientist at Google DeepMind
2014
Xin Tong, Associate Prof. at USC
2012
Lazar Atanackovic, Assistant Prof. at U. of Alberta
2025-26
Subhodh Kotekal, Quant at CTC
2025-26
Tudor Manole, Assistant Prof. at Stanford
2024-26
Nicholas Nelsen, Assistant Prof. at UT Austin
2024-25
Ziang Chen, xAI
2023-25
Yajit Jain, Senior Machine Learning Scientist at Broad Institute
2023-25
Anya Katsevich, Assistant Prof. at Duke Univ.
2022-25
Yuling Yan, Quant at D. E. Shaw
2023-24
Borjan Geshkovski, Researcher at INRIA
2023-23
Yanjun Han, Assistant Prof. at NYU
2022-23
Tyler Maunu, Assistant Prof. at Brandeis
2018-21
Jingbo Liu, Assistant Prof. at UIUC
2018-20
Andrej Risteski, Associate Prof. at CMU
2017-19
Geoffrey Schiebinger, Associate Prof. at UBC
2016-19
Elina Robeva, Associate Prof. at UBC
2016-19
Victor-Emmanuel Brunel, Professor at ENSAE
2015-18
Irène Waldspurger, Researcher at CNRS
2016-17
Afonso Bandeira, Professor at ETH-Zürich
2015-16

Openings

Interested in joining our group?

I receive many inquiries from highly qualified candidates, so I am not able to respond individually to emails asking whether I will be taking Ph.D. students or postdocs in the fall.

In principle, I am always evaluating complete applications in my areas of expertise, but decisions are made through the appropriate departmental process, and I cannot assess individual cases before seeing recommendation letters, transcripts, and research statements. The best first step is to identify the most appropriate position and apply; once you have applied, there is no need to contact me separately, but please flag me as a reader in your application.

I do not host interns.

C.L.E Moore Instructor

Applied Mathematics

Competitive 3yr postdoc with higher salary and teaching duties

Postdoc

Eric & Wendy Schmidt center

I am looking for postdocs interested in exploring new connections between mathematical methods and biology, esp. genomics. The new Eric & Wendy Schmidt postdocs offers a perfect opportunity for such collaborations.

Wiener Fellowship

Statistics and Data Scence Center

The Wiener Fellowship is a competitive postdoc in the Statistics and Data Science Center at MIT. Laureates are expected to collaborate with several members of the center

Postdoc

School of Science

The School of Science's 3-year Postdoctoral Fellowship is aimed at scholars engaged in cross-disciplinary research.

Ph.D student

Mathematics department

This group admits Ph.D. students exclusively through the Mathematics department at MIT. Decisions are made at the departmental level rather than at the faculty level.

Current Funding

NSF DMS-2509011

Theoretical Foundations of Efficient and Scalable Graph Learning

Contact

The best way to contact me is via email

View Email Address