V
Venkat Chandrasekaran
Researcher at California Institute of Technology
Publications - 85
Citations - 6012
Venkat Chandrasekaran is an academic researcher from California Institute of Technology. The author has contributed to research in topics: Convex optimization & Graphical model. The author has an hindex of 25, co-authored 77 publications receiving 5468 citations. Previous affiliations of Venkat Chandrasekaran include Massachusetts Institute of Technology.
Papers
More filters
Journal ArticleDOI
The Convex Geometry of Linear Inverse Problems
TL;DR: This paper provides a general framework to convert notions of simplicity into convex penalty functions, resulting in convex optimization solutions to linear, underdetermined inverse problems.
Journal ArticleDOI
Rank-Sparsity Incoherence for Matrix Decomposition
TL;DR: In this paper, a matrix that is formed by adding an unknown sparse matrix to an unknown low-rank matrix is decomposed into its sparse and low rank components, and the goal is to decompose the given matrix into its low rank and sparse components.
Journal Article
Rank-Sparsity Incoherence for Matrix Decomposition
TL;DR: In this paper, rank-sparsity incoherence is defined as an uncertainty principle between the sparsity pat- tern of a matrix and its row and column spaces, and used to characterize both fundamental identifiability as well as (deterministic) sufficient conditions for exact recovery.
Journal ArticleDOI
Latent variable graphical model selection via convex optimization
TL;DR: In this paper, a convex program based on regularized maximum-likelihood was proposed for model selection in the latent-variable Gaussian graphical model setting, with the conditional statistics of the observed variables conditioned on the latent variables being specified by a graphical model.
Journal ArticleDOI
Computational and statistical tradeoffs via convex relaxation
TL;DR: This paper defines a notion of “algorithmic weakening,” in which a hierarchy of algorithms is ordered by both computational efficiency and statistical efficiency, allowing the growing strength of the data at scale to be traded off against the need for sophisticated processing.