← Back to papers
2011 NIPS NeurIPS 2011

On the accuracy of l1-filtering of signals with block-sparse structure

Abstract

We discuss new methods for the recovery of signals with block-sparse structure, based on l1-minimization. Our emphasis is on the efficiently computable error bounds for the recovery routines. We optimize these bounds with respect to the method parameters to construct the estimators with improved statistical properties. We justify the proposed approach with an oracle inequality which links the properties of the recovery algorithms and the best estimation performance.

🌉 Interdisciplinary Bridge — Machine Learning and Mathematics & Optimization
🧭 Keyword Pioneer — block-sparse signals
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Deep Learning, Machine Learning, Mathematics & Optimization, Reinforcement Learning
📈 Trend Setter — Sparse Coding

Authors

Fatma K. Karzan , Arkadi S. Nemirovski , Boris T. Polyak , Anatoli Juditsky

Topics

Machine Learning > Core Methods > Regression Machine Learning > Optimization & Theory > Optimization Machine Learning > Optimization & Theory > Statistical Learning Mathematics & Optimization > Optimization > Continuous Optimization Machine Learning > Core Methods > Feature Selection Machine Learning > Optimization & Theory > Statistics Mathematics & Optimization > Optimization > Sparse Optimization Machine Learning > Core Methods > Sparse Coding

Keywords

oracle inequality statistical estimation signal recovery block-sparse signals l1-minimization l1 minimization error bound block sparsity
Download PDF

Related papers

Co-Training for Domain Adaptation 2011
The Local Rademacher Complexity of Lp-Norm Multiple Kernel Learning 2011
Learning to Agglomerate Superpixel Hierarchies 2011
A Reinforcement Learning Theory for Homeostatic Regulation 2011
A Global Structural EM Algorithm for a Model of Cancer Progression 2011