R
Robert M. Freund
Researcher at Massachusetts Institute of Technology
Publications - 132
Citations - 8537
Robert M. Freund is an academic researcher from Massachusetts Institute of Technology. The author has contributed to research in topics: Convex optimization & Linear programming. The author has an hindex of 33, co-authored 129 publications receiving 8056 citations. Previous affiliations of Robert M. Freund include Stanford University & University of Michigan.
Papers
More filters
Posted Content
Condition Number Analysis of Logistic Regression, and its Implications for Standard First-Order Solution Methods.
TL;DR: This paper introduces a pair of condition numbers that measure the degree of non-separability or separability of a given dataset in the setting of binary classification, and studies how these condition numbers relate to and inform the properties and the convergence guarantees of first-order methods.
Journal ArticleDOI
Functional Regression for State Prediction Using Linear PDE Models and Observations
TL;DR: In this paper, the authors introduce a functional regression method that incorporates observations into a deterministic linear Partial Differential Equation (PDE) model to improve its prediction of the true state.
Posted Content
Analysis of the Frank-Wolfe Method for Logarithmically-Homogeneous Barriers, with an Extension
Renbo Zhao,Robert M. Freund +1 more
TL;DR: A new analysis of the Frank-Wolfe method proposed in Dvurechensky et al. applied to constrained minimization problems where the objective function $f$ is a $\theta$-logarithmically-homogeneous self-concordant barrier.
Journal ArticleDOI
Binary Optimization Techniques for Linear PDE-governed Material Design
TL;DR: It is shown herein that binary optimization combined with a reduced basis approach can relatively efficiently produce good solutions to material design problems of interest.
Posted Content
Analysis of the Frank-Wolfe Method for Convex Composite Optimization involving a Logarithmically-Homogeneous Barrier
TL;DR: In this paper, a new generalized Frank-Wolfe method was proposed for the composite optimization problem, which is equivalent to an adaptive-step-size mirror descent method applied to the dual problem.