-

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

UPCOMING EVENTS

mifods seminar

Carlos Fernandez-Granda (NYU)

TBA

TBA
mifods seminar

Shai Shalev-Shwartz (HUJI)

TBA

TBA
mifods seminar

Workshop on Sublinear Algorithms and robust statistics

Workshop on the Spring 18 semester's theme: Sublinear Algorithms and robust statistics

Research

5 semesters = 5 themes

Spring 18

Sublinear algorithms, local algorithms and robust statistics

Fall 18

Non-convex optimization and deep learning

Spring 19

Graphical models, Exchangeable models and Graphons

Fall 19

Learning under complex structure

Spring 20

Statistical and Computational Tradeoffs

TRIPODS+X

The NSF is calling for proposals of partnerships between Science and Engineering Fields and MIFODS. If you would like to propose, contact a MIFODS investigator.
-

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