Increasingly, optimization problems in machine learning, especially those arising from bigh-dimensional statistical estimation, bave a large number of variables. Modem statistical estimators developed over the past decade have statistical or sample complexity that depends only weakly on the number of parameters when there is some structore to the problem, such as sparsity. A central question is...

Nonnegative matrix factorization (NMF) has become a ubiquitous tool for data analysis. An important variant is the sparse NMF problem which arises when we explicitly require the learnt features to be sparse. A natural measure of sparsity is the L0 norm, however its optimization is NP-hard. Mixed norms, such as L1/L2 measure, have been shown to model sparsity robustly, based on intuitive attribu...

We address the problem of sparse selection in linear models. A number of nonconvex penalties have been proposed in the literature for this purpose, along with a variety of convex-relaxation algorithms for finding good solutions. In this article we pursue a coordinate-descent approach for optimization, and study its convergence properties. We characterize the properties of penalties suitable for...

Recently several methods were proposed for sparse optimization which make careful use of second-order information [11, 34, 20, 4] to improve local convergence rates. These methods construct a composite quadratic approximation using Hessian information, optimize this approximation using a first-order method, such as coordinate descent and employ a line search to ensure sufficient descent. Here w...

Recently several, so-called, proximal Newton methods were proposed for sparse optimization [6, 11, 8, 3]. These methods construct a composite quadratic approximation using Hessian information, optimize this approximation using a first-order method, such as coordinate descent and employ a line search to ensure sufficient descent. Here we propose a general framework, which includes slightly modif...

In this paper we generalize the framework of the feasible descent method (FDM) to a randomized (R-FDM) and a coordinate-wise random feasible descent method (RC-FDM) framework. We show that the famous SDCA algorithm for optimizing the SVM dual problem, or the stochastic coordinate descent method for the LASSO problem, fits into the framework of RC-FDM. We prove linear convergence for both R-FDM ...

In this paper we generalize the framework of the Feasible Descent Method (FDM) to a Randomized (R-FDM) and a Randomized Coordinate-wise Feasible Descent Method (RCFDM) framework. We show that many machine learning algorithms, including the famous SDCA algorithm for optimizing the SVM dual problem, or the stochastic coordinate descent method for the LASSO problem, fits into the framework of RC-F...

We use differential equations based approaches to provide some physics insights into analyzing the dynamics of popular optimization algorithms in machine learning. In particular, we study gradient descent, proximal gradient descent, coordinate gradient descent, proximal coordinate gradient, and Newton’s methods as well as their Nesterov’s accelerated variants in a unified framework motivated by...

We propose Shotgun, a parallel coordinate descent algorithm for minimizing L1regularized losses. Though coordinate descent seems inherently sequential, we prove convergence bounds for Shotgun which predict linear speedups, up to a problemdependent limit. We present a comprehensive empirical study of Shotgun for Lasso and sparse logistic regression. Our theoretical predictions on the potential f...