K
Karthik Mohan
Researcher at University of Washington
Publications - 23
Citations - 1293
Karthik Mohan is an academic researcher from University of Washington. The author has contributed to research in topics: Graphical model & Convex optimization. The author has an hindex of 12, co-authored 19 publications receiving 1195 citations.
Papers
More filters
Journal Article
Iterative reweighted algorithms for matrix rank minimization
Karthik Mohan,Maryam Fazel +1 more
TL;DR: This paper proposes a family of Iterative Reweighted Least Squares algorithms IRLS-p, and gives theoretical guarantees similar to those for nuclear norm minimization, that is, recovery of low-rank matrices under certain assumptions on the operator defining the constraints.
Journal Article
Node-based learning of multiple Gaussian graphical models
TL;DR: This work takes a node-based approach to estimation of high-dimensional Gaussian graphical models corresponding to a single set of variables under several distinct conditions, and derives a set of necessary and sufficient conditions that allows the problem to decompose into independent subproblems so that the algorithm can be scaled to high- dimensional settings.
Proceedings ArticleDOI
Reweighted nuclear norm minimization with application to system identification
Karthik Mohan,Maryam Fazel +1 more
TL;DR: This paper analyzes the convergence of Reweighted trace minimization as an iterative heuristic for matrix rank minimization, and proposes an efficient gradient-based implementation that takes advantage of the new formulation and opens the way to solving large-scale problems.
Proceedings ArticleDOI
Iterative reweighted least squares for matrix rank minimization
Karthik Mohan,Maryam Fazel +1 more
TL;DR: This paper extends IRLS-p as a family of algorithms for the matrix rank minimization problem and presents a relatedfamily of algorithms, sIRLS- p, which performs better than algorithms such as Singular Value Thresholding on a range of ‘hard’ problems (where the ratio of number of degrees of freedom in the variable to the number of measurements is large).
Posted Content
A Simplified Approach to Recovery Conditions for Low Rank Matrices
TL;DR: In this paper, the authors show how several robust classes of recovery conditions can be extended from vectors to matrices in a simple and transparent way, leading to the best known restricted isometry and nullspace conditions for matrix recovery.