Average Case Analysis of High-Dimensional Block-Sparse Recovery and Regression for Arbitrary Designs
نویسندگان
چکیده
This paper studies conditions for highdimensional inference when the set of observations is given by a linear combination of a small number of groups of columns of a design matrix, termed the “block-sparse” case. In this regard, it first specifies conditions on the design matrix under which most of its block submatrices are well conditioned. It then leverages this result for average-case analysis of high-dimensional block-sparse recovery and regression. In contrast to earlier works: (i) this paper provides conditions on arbitrary designs that can be explicitly computed in polynomial time, (ii) the provided conditions translate into near-optimal scaling of the number of observations with the number of active blocks of the design matrix, and (iii) the conditions suggest that the spectral norm, rather than the column/block coherences, of the design matrix fundamentally limits the performance of computational methods in high-dimensional settings.
منابع مشابه
Mammalian Eye Gene Expression Using Support Vector Regression to Evaluate a Strategy for Detecting Human Eye Disease
Background and purpose: Machine learning is a class of modern and strong tools that can solve many important problems that nowadays humans may be faced with. Support vector regression (SVR) is a way to build a regression model which is an incredible member of the machine learning family. SVR has been proven to be an effective tool in real-value function estimation. As a supervised-learning appr...
متن کاملRobust Estimation in Linear Regression with Molticollinearity and Sparse Models
One of the factors affecting the statistical analysis of the data is the presence of outliers. The methods which are not affected by the outliers are called robust methods. Robust regression methods are robust estimation methods of regression model parameters in the presence of outliers. Besides outliers, the linear dependency of regressor variables, which is called multicollinearity...
متن کاملRecovery of signals by a weighted $\ell_2/\ell_1$ minimization under arbitrary prior support information
In this paper, we introduce a weighted l2/l1 minimization to recover block sparse signals with arbitrary prior support information. When partial prior support information is available, a sufficient condition based on the high order block RIP is derived to guarantee stable and robust recovery of block sparse signals via the weighted l2/l1 minimization. We then show if the accuracy of arbitrary p...
متن کاملSimultaneous support recovery in high dimensions: Benefits and perils of block l1/l∞-regularization
Given a collection of r ≥ 2 linear regression problems in p dimensions, suppose that the regression coefficients share partially common supports of size at most s. This set-up suggests the use of l1/l∞-regularized regression for joint estimation of the p × r matrix of regression coefficients. We analyze the high-dimensional scaling of l1/l∞-regularized quadratic programming, considering both co...
متن کاملFinite Frames for Sparse Signal Processing
Over the last decade, considerable progress has been made towards developing new signal processing methods to manage the deluge of data caused by advances in sensing, imaging, storage, and computing technologies. Most of these methods are based on a simple but fundamental observation. That is, highdimensional data sets are typically highly redundant and live on low-dimensional manifolds or subs...
متن کامل