Robert M. Freund

About

Robert M. Freund is the Theresa Seley Professor in Management Science and a Professor of Operations Research at the MIT Sloan School of Management. His main research interests include convex optimization, computational complexity, convex geometry, large-scale nonlinear optimization, and related mathematical systems. His recent work focuses on first-order methods and their connections to statistical and machine learning. Freund has served as coeditor of the journal Mathematical Programming and as associate editor for several optimization and operations research journals. He has held leadership roles such as Co-Director of the MIT Operations Research Center, the MIT Program in Computation for Design and Optimization, and Chair of the INFORMS Optimization Section. Freund received his BA in mathematics from Princeton University and his MS and PhD in operations research from Stanford University. He has been recognized with awards including the Longuet-Higgins Prize in computer vision and the MIT Seegal Prize for inspiring students to pursue and achieve excellence.

Research topics

• Computer Science
• Artificial Intelligence
• Mathematical optimization
• Mathematics
• Algorithm
• Applied mathematics
• Combinatorics

Selected publications

• A new perspective on boosting in linear regression via subgradient optimization and relatives

  Project Euclid (Cornell University) · 2017-12-01 · 35 citations

  articleOpen access1st authorCorresponding

  We analyze boosting algorithms [Ann. Statist. 29 (2001) 1189–1232; Ann. Statist. 28 (2000) 337–407; Ann. Statist. 32 (2004) 407–499] in linear regression from a new perspective: that of modern first-order methods in convex optimization. We show that classic boosting algorithms in linear regression, namely the incremental forward stagewise algorithm ($\\text{FS}_{\\varepsilon}$) and least squares boosting [LS-BOOST$(\\varepsilon)$], can be viewed as subgradient descent to minimize the loss functi…

  PublisherOA PDFDOI

• Generalized stochastic Frank–Wolfe algorithm with stochastic “substitute” gradient for structured convex optimization

  Mathematical Programming · 2020 · 19 citations

  Senior authorCorresponding
  PublisherDOI

• Analysis of the Frank–Wolfe method for convex composite optimization involving a logarithmically-homogeneous barrier

  Mathematical Programming · 2022 · 15 citations

  Senior authorCorresponding

  Abstract We present and analyze a new generalized Frank–Wolfe method for the composite optimization problem $$(P): {\min }_{x\in {\mathbb {R}}^n} \; f(\mathsf {A} x) + h(x)$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:mrow><mml:mrow><mml:mo>(</mml:mo><mml:mi>P</mml:mi><mml:mo>)</mml:mo></mml:mrow><mml:mo>:</mml:mo><mml:msub><mml:mo>min</mml:mo><mml:mrow><mml:mi>x</mml:mi><mml:mo>∈</mml:mo><mml:msup><mml:mrow><mml:mi>R</mml:mi></mml:mrow><mml:mi>n</mml:mi></mml:msup></mml:mrow>…

  PublisherOA PDFDOI

• Accelerated Residual Methods for the Iterative Solution of Systems of Equations

  SIAM Journal on Scientific Computing · 2018-01-01 · 10 citations

  articleOpen access

  We present accelerated residual methods for the iterative solution of systems of equations by leveraging recent developments in accelerated gradient methods for convex optimization. The stability properties of the proposed method are analyzed for linear systems of equations by using the finite difference equation theory. Next, we introduce a residual descent restarting strategy and an adaptive computation of the acceleration parameter to enhance the robustness and efficiency of our method. Furth…

  PublisherOA PDFDOI

• Accelerating Greedy Coordinate Descent Methods

  arXiv (Cornell University) · 2018-06-07 · 10 citations

  preprintOpen access

  We study ways to accelerate greedy coordinate descent in theory and in practice, where "accelerate" refers either to $O(1/k^2)$ convergence in theory, in practice, or both. We introduce and study two algorithms: Accelerated Semi-Greedy Coordinate Descent (ASCD) and Accelerated Greedy Coordinate Descent (AGCD). While ASCD takes greedy steps in the $x$-updates and randomized steps in the $z$-updates, AGCD is a straightforward extension of standard greedy coordinate descent that only takes greedy s…

  PublisherOA PDFDOI

Frequent coauthors

• Paul Grigas

  18 shared

• Alexandre Belloni

  15 shared

• Han Men

  American Institute of Aeronautics and Astronautics

  14 shared

• J. Peraire

  Massachusetts Institute of Technology

  13 shared

• Rahul Mazumder

  Massachusetts Institute of Technology

  13 shared

• Ngoc Cuong Nguyen

  10 shared

• Haihao Lu

  10 shared

• Fernando Ordóñez

  8 shared

Awards & honors

• MIT’s 2020 Seegal prize
• INFORMS Fellow (2018)
• Longuet-Higgins Prize in computer vision (2007)
• Samuel M. Seegal Faculty Prize

Similar researchers at Massachusetts Institute of Technology

• Dimitris Bertsimash-91
• James B. Orlinh-60
• Thomas Magnantih-44