Bayesian L1-Norm Sparse Learning

Simple item page
dc.contributor.authorLee, Daniel D
dc.contributor.authorLin, Yuanqing
dc.date2023-05-17T00:49:05.000
dc.date.accessioned2023-05-22T19:07:01Z
dc.date.available2023-05-22T19:07:01Z
dc.date.issued2006-05-19
dc.date.submitted2007-04-16T08:17:25-07:00
dc.description.abstractWe propose a Bayesian framework for learning the optimal regularization parameter in the L1-norm penalized least-mean-square (LMS) problem, also known as LASSO [1] or basis pursuit [2]. The setting of the regularization parameter is critical for deriving a correct solution. In most existing methods, the scalar regularization parameter is often determined in a heuristic manner; in contrast, our approach infers the optimal regularization setting under a Bayesian framework. Furthermore, Bayesian inference enables an independent regularization scheme where each coefficient (or weight) is associated with an independent regularization parameter. Simulations illustrate the improvement using our method in discovering sparse structure from noisy data.
dc.description.commentsCopyright 2006 IEEE. Reprinted from Proceedings of the 2006 IEEE International Conference Acoustics, Speech and Signal Processing, Volume 5, pages V605-V608. Publisher URL: http://dx.doi.org/10.1109/ICASSP.2006.1661348 This material is posted here with permission of the IEEE. Such permission of the IEEE does not in any way imply IEEE endorsement of any of the University of Pennsylvania's products or services. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to pubs-permissions@ieee.org. By choosing to view this document, you agree to all provisions of the copyright laws protecting it.
dc.identifier.urihttps://repository.upenn.edu/handle/20.500.14332/33422
dc.legacy.articleid1254
dc.legacy.fulltexturlhttps://repository.upenn.edu/cgi/viewcontent.cgi?article=1254&context=ese_papers&unstamped=1
dc.source.issue230
dc.source.journalDepartmental Papers (ESE)
dc.source.peerreviewedtrue
dc.source.statuspublished
dc.subject.otherGRASP
dc.titleBayesian L1-Norm Sparse Learning
dc.typePresentation
digcom.identifierese_papers/230
digcom.identifier.contextkey293524
digcom.identifier.submissionpathese_papers/230
digcom.typeconference
dspace.entity.typePublication
relation.isAuthorOfPublication044c3dcb-cd50-41da-8642-3534e2c77660
relation.isAuthorOfPublication.latestForDiscovery044c3dcb-cd50-41da-8642-3534e2c77660
upenn.schoolDepartmentCenterDepartmental Papers (ESE)
upenn.schoolDepartmentCenterGeneral Robotics, Automation, Sensing and Perception Laboratory
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
lin.pdf
Size:
544.38 KB
Format:
Adobe Portable Document Format
Download
Collection
Presentations