Learning Model-Based Sparsity via Projected Gradient DescentReport as inadecuate



 Learning Model-Based Sparsity via Projected Gradient Descent


Learning Model-Based Sparsity via Projected Gradient Descent - Download this document for free, or read online. Document in PDF available to download.

Download or read this book online for free in PDF: Learning Model-Based Sparsity via Projected Gradient Descent
Several convex formulation methods have been proposed previously for statistical estimation with structured sparsity as the prior. These methods often require a carefully tuned regularization parameter, often a cumbersome or heuristic exercise. Furthermore, the estimate that these methods produce might not belong to the desired sparsity model, albeit accurately approximating the true parameter. Therefore, greedy-type algorithms could often be more desirable in estimating structured-sparse parameters. So far, these greedy methods have mostly focused on linear statistical models. In this paper we study the projected gradient descent with non-convex structured-sparse parameter model as the constraint set. Should the cost function have a Stable Model-Restricted Hessian the algorithm produces an approximation for the desired minimizer. As an example we elaborate on application of the main results to estimation in Generalized Linear Model.



Author: Sohail Bahmani; Petros T. Boufounos; Bhiksha Raj

Source: https://archive.org/







Related documents