-

ABOUT MIFODS

The MIT Institute for Foundations of Data Science (MIFODS) is an NSF funded interdisciplinary effort to develop the theoretical foundations of data science through integrated research and training activities. To achieve this goal, MIFODS stimulates research and educational interactions between mathematics, statistics and theoretical computer science, both within MIT and in the research community at large.
investigators
semester-long themes
Departments
Cups of Coffee

Research

The five research themes of MIFODS
Sublinear algorithms, local algorithms and robust statistics

Sublinear algorithms, local algorithms and robust statistics

Statistical and Computational Tradeoffs

Statistical and Computational Tradeoffs

Learning under complex structure

Learning under complex structure

Non-convex optimization and deep learning

Non-convex optimization and deep learning

Graphical models, Exchangeable models and Graphons

Graphical models, Exchangeable models and Graphons

Join us!

Post-doctoral fellowship starting July 2018 available Apply now

Members

Meet the MIFODS investigators
Tamara Broderick

Tamara Broderick

EECS
Guy Bresler

Guy Bresler

EECS
Victor Chernozhukov

Victor Chernozhukov

Economics
Costis Daskalakis

Costis Daskalakis

EECS
David Gamarnik

David Gamarnik

Sloan
Piotr Indyk

Piotr Indyk

EECS
Tommi Jaakkola

Tommi Jaakkola

EECS
Stefanie Jegelka

Stefanie Jegelka

EECS
Jonathan Kelner

Jonathan Kelner

Mathematics
Aleksandr Madry

Aleksander Madry

EECS
Ankur Moitra

Ankur Moitra

Mathematics
Elchanan Mossel

Elchanan Mossel

Mathematics
Pablo Parrilo

Pablo Parrilo

EECS
Philippe Rigollet

Philippe Rigollet

Mathematics
Ronitt Rubinfeld

Ronitt Rubinfeld

EECS
Devavrat Shah

Devavrat Shah

EECS
Suvrit Sra

Suvrit Sra

EECS
Caroline Uhler

Caroline Uhler

EECS