PPT-Online Performance Guarantees for Sparse Recovery

Raja Giryes ICASSP 2011 Volkan Cevher Agenda The sparse approximation problem Algorithms and prerun guarantees Online performance guarantees Performance bound Parameter selection 2 Sparse approximation. Such matrices has several attractive properties they support algorithms with low computational complexity and make it easy to perform in cremental updates to signals We discuss applications to several areas including compressive sensing data stream Adaptivity. in Sparse Recovery. Piotr. . Indyk. MIT. Joint work . with Eric . Price and David Woodruff, 2011.. Sparse recovery. (approximation theory, statistical model selection, information-based complexity, learning Fourier . Volkan . Cevher. volkan.cevher@epfl.ch. Laboratory. for Information . . and Inference Systems - . LIONS. . http://lions.epfl.ch. Linear Dimensionality Reduction. Compressive sensing. non-adaptive measurements. Aswin C Sankaranarayanan. Rice University. Richard G. . Baraniuk. Andrew E. Waters. Background subtraction in surveillance videos. s. tatic camera with foreground objects. r. ank 1 . background. s. parse. Compressive Sensing of Videos. Venue. CVPR 2012, Providence, RI, USA. June 16, 2012. Organizers. :. Richard G. . Baraniuk. Mohit. Gupta. Aswin C. Sankaranarayanan. Ashok Veeraraghavan. Part 2: Compressive sensing. 26. th. . August 2013. Abdul Yassim. Vice President. Trade and Working Capital. 1. Absa presentation. title .  Date of presentation. Company confidential use only / Unrestricted distribution. . Recovery. . (. Using . Sparse. . Matrices). Piotr. . Indyk. MIT. Heavy Hitters. Also called frequent elements and elephants. Define. HH. p. φ. . (. x. ) = { . i. : |x. i. | ≥ . φ. ||. x||. p. Adaptivity. in Sparse Recovery. Piotr. . Indyk. MIT. Joint work . with Eric . Price and David Woodruff, 2011.. Sparse recovery. (approximation theory, statistical model selection, information-based complexity, learning Fourier . Compressive. Sensing. Volkan . Cevher. volkan@rice.edu. Marco Duarte. Chinmay Hegde. Richard . Baraniuk. Dimensionality Reduction. Compressive sensing. non-adaptive measurements. Sparse Bayesian learning. onto convex sets. Volkan. Cevher. Laboratory. for Information . . and Inference Systems – . LIONS / EPFL. http://lions.epfl.ch . . joint work with . Stephen Becker. Anastasios. . Kyrillidis. ISMP’12. University . of Edinburgh – . Scotland. Remi. . Gribonval. ,. INRIA, . Rennes – . France. The Analysis . Cosparse. Model . for Signals and Images. Michael . Elad. , . Technion. ,. Haifa – . Israel. . Jeremy Watt and . Aggelos. . Katsaggelos. Northwestern University. Department of EECS. Part 2: Quick and dirty optimization techniques. Big picture – a story of 2’s. 2 excellent greedy algorithms: . Yi Ma. 1,2. . Allen Yang. 3. John . Wright. 1. CVPR Tutorial, June 20, 2009. 1. Microsoft Research Asia. 3. University of California Berkeley. 2. University of Illinois . at Urbana-Champaign. Exhibit Page 1of 4EXHIBIT -FORMS OF PERFORMANCE GUARANTEESPART 1 FORM OF PERFORMANCE GUARANTEE PARENT COMPANYTHIS PERFORMANCE GUARANTEE AGREEMENT hereinafter referred to as the Guarantee effective on