activity
20042008
most citedHigh-Dimensional Graphical Model Selection Using -Regularized Logistic Regression

62 citations · 226 across the 13 of their papers we have counts for

collaborators

13 papers

stat.ML200849 cited

High-dimensional covariance estimation by minimizing -penalized log-determinant divergence

Pradeep Ravikumar, Martin J. Wainwright, Garvesh Raskutti +1

Given i.i.d. observations of a random vector , we study the problem of estimating both its covariance matrix , and its inverse covariance or concentration…

cs.IT2008

Lower Bounds on the Rate-Distortion Function of LDGM Codes

A. G. Dimakis, M. J. Wainwright, K. Ramchandran

A recent line of work has focused on the use of low-density generator matrix (LDGM) codes for lossy source coding. In this paper, wedevelop a generic technique for deriving lower b…

math.ST200811 cited

Information-theoretic limits on sparse signal recovery: Dense versus sparse measurement matrices

Wei Wang, Martin J. Wainwright, Kannan Ramchandran

We study the information-theoretic limits of exactly recovering the support of a sparse signal using noisy projections defined by various classes of measurement matrices. Our analy…

stat.ML200813 cited

High-dimensional subset recovery in noise: Sparsified measurements without loss of statistical efficiency

Dapo Omidiran, Martin J. Wainwright

We consider the problem of estimating the support of a vector based on observations contaminated by noise. A significant body of work has studied behavior…

cs.IT200814 cited

Network-based consensus averaging with general noisy channels

Ram Rajagopal, Martin J. Wainwright

This paper focuses on the consensus averaging problem on graphs under general noisy channels. We study a particular class of distributed consensus algorithms based on damped update…

math.ST200862 cited

High-Dimensional Graphical Model Selection Using -Regularized Logistic Regression

Pradeep Ravikumar, Martin J. Wainwright, John D. Lafferty

We consider the problem of estimating the graph structure associated with a discrete Markov random field. We describe a method based on -regularized logistic regression, in…