Pradeep Ravikumar

A unified framework for high-dimensional analysis of M-estimators with decomposable regularizers

High-dimensional statistical inference deals with models in which the the number of parameters p is comparable to or larger than the sample size n. Since it is usually impossible to obtain consistent procedures unless p/n → 0, a line of recent work has studied models with various types of structure (e.g., sparse vectors; block-structured matrices; low-rank matrices; Markov assumptions). In such settings, a general approach to estimation is to solve a regularized convex program (known as a regularized M-estimator) which combines a loss function (measuring how well the model fits the data) with some regularization function that encourages the assumed structure. The goal of this paper is to provide a unified framework for establishing consistency and convergence rates for such regularized M-estimators under high-dimensional scaling. We state one main theorem and show how it can be used to re-derive several existing results, and also to obtain several new results on consistency and convergence rates. Our analysis also identifies two key properties of loss and regularization functions, referred to as restricted strong convexity and decomposability, that ensure the corresponding regularized M-estimators have fast convergence rates.

High-dimensional Ising model selection using ℓ1-regularized logistic regression

We consider the problem of estimating the graph associated with a binary Ising Markov random field. We describe a method based on

Adaptive name matching in information integration

\ell_1

HIGH-DIMENSIONAL COVARIANCE ESTIMATION BY MINIMIZING ℓ1-PENALIZED LOG-DETERMINANT DIVERGENCE

-regularized logistic regression, in which the neighborhood of any given node is estimated by performing logistic regression subject to an

Information-Theoretic Lower Bounds on the Oracle Complexity of Stochastic Convex Optimization

\ell_1

Error-correcting tournaments

-constraint. The method is analyzed under high-dimensional scaling in which both the number of nodes

Encoding and decoding V1 fMRI responses to natural images with sparse nonparametric models

p

A Dirty Model for Multiple Sparse Regression

and maximum neighborhood size

Learning-based analytical cross-platform performance prediction

d

On the difficulty of learning power law graphical models

are allowed to grow as a function of the number of observations