Robert M. Freund

Also known as Robert Freund

Robert Freund is an MIT Sloan professor whose optimization research connects computer vision and machine learning. He studied mathematics at Princeton and operations research at Stanford, published work on variable-dimension complexes and support-vector-machine face detection, and coauthored a management-science textbook with Dimitris Bertsimas. He received the Longuet-Higgins Prize in computer vision in 2007 and served as MIT Sloan deputy dean from 2008 to 2011 before becoming an INFORMS Fellow in 2018. In 2022, he and Zikai Xiong proposed Taylor-approximated gradients for Frank-Wolfe methods in empirical risk minimization. As of October 2026, he is the Theresa Seley Professor in Management Science and a Professor of Operations Research at MIT Sloan.

Now at: Massachusetts Institute of Technology
Works: 213
Citations: 7,815
h-index: 32
Badges: Loyal

Publication numbers from OpenAlex, as of 22 October 2026.

Timeline

1984

Variable Dimension Complexes

Freund holds a BA in mathematics from Princeton University and an MS and a PhD in operations research from Stanford University. In 1984, he publishes “Variable Dimension Complexes, Part I: Basic Theory.”
June 1997

SVMs for Face Detection

In June 1997, he publishes “Training Support Vector Machines: an Application to Face Detection” with Edgar Osuna and Federico Girosi in the IEEE Computer Society Conference on Computer Vision and Pattern Recognition.
July 2004

Data, Models, and Decisions

In July 2004, he and Dimitris Bertsimas coauthor the textbook “Data, Models and Decisions.” It introduces decision-support systems through real-world applications and spreadsheet models.
2007

A Longuet-Higgins Prize

In 2007, he receives the Longuet-Higgins Prize in computer vision.
2008–2011

Deputy Dean at MIT Sloan

He serves as Deputy Dean of the Sloan School at MIT from 2008 to 2011.
2018

An INFORMS Fellowship

In 2018, he is elected an INFORMS Fellow.
2022

Taylor Gradients for Frank-Wolfe

In 2022, with Zikai Xiong, he proposes Taylor series-approximated gradients for Frank-Wolfe methods in empirical risk minimization, a problem in statistical and machine learning.
As of October 2026

Professor at MIT Sloan

As of October 2026, he is the Theresa Seley Professor in Management Science and a Professor of Operations Research at the MIT Sloan School of Management. In August 2026, he coauthors “Symmetry-dependence in Rounding of a Convex Body” with Zikai Xiong.