Iterative Greedy LMI for Sparse Control

Sparse Signals Reconstruction via Adaptive Iterative Greedy Algorithm

Compressive sensing(CS) is an emerging research field that has applications in signal processing, error correction, medical imaging, seismology, and many more other areas. CS promises to efficiently reconstruct a sparse signal vector via a much smaller number of linear measurements than its dimension. In order to improve CS reconstruction performance, this paper present a novel reconstruction g...

Phase Transitions for Greedy Sparse Approximation Algorithms

A major enterprise in compressed sensing and sparse approximation is the design and analysis of computationally tractable algorithms for recovering sparse, exact or approximate, solutions of underdetermined linear systems of equations. Many such algorithms have now been proven using the ubiquitous Restricted Isometry Property (RIP) [9] to have optimal-order uniform recovery guarantees. However,...

Sparse Greedy Matrix Approximation for Machine Learning

Greedy Algorithms for Sparse Reinforcement Learning

Feature selection and regularization are becoming increasingly prominent tools in the efforts of the reinforcement learning (RL) community to expand the reach and applicability of RL. One approach to the problem of feature selection is to impose a sparsity-inducing form of regularization on the learning method. Recent work on L1 regularization has adapted techniques from the supervised learning...

Greedy algorithms for Sparse Dictionary Learning

Background. Sparse dictionary learning is a kind of representation learning where we express the data as a sparse linear combination of an overcomplete basis set. This is usually formulated as an optimization problem which is known to be NP-Hard. A typical solution uses a two-step iterative procedure which involves either a convex relaxation or some clustering based solution. One problem with t...