Open problem: Tightness of maximum likelihood semidefinite relaxations

Author(s): Bandeira, Afonso S; Khoo, Yuehaw; Singer, Amit

Download

To refer to this page use: http://arks.princeton.edu/ark:/88435/pr14m9n

Full metadata record

DC Field	Value	Language
dc.contributor.author	Bandeira, Afonso S	-
dc.contributor.author	Khoo, Yuehaw	-
dc.contributor.author	Singer, Amit	-
dc.date.accessioned	2019-08-29T17:01:53Z	-
dc.date.available	2019-08-29T17:01:53Z	-
dc.date.issued	2014	en_US
dc.identifier.citation	Bandeira, A.S., Khoo, Y. & Singer, A.. (2014). Open Problem: Tightness of maximum likelihood semidefinite relaxations. Proceedings of The 27th Conference on Learning Theory, in PMLR 35:1265-1267	en_US
dc.identifier.uri	http://arks.princeton.edu/ark:/88435/pr14m9n	-
dc.description.abstract	We have observed an interesting, yet unexplained, phenomenon: Semidefinite programming (SDP) based relaxations of maximum likelihood estimators (MLE) tend to be tight in recovery problems with noisy data, even when MLE cannot exactly recover the ground truth. Several results establish tightness of SDP based relaxations in the regime where exact recovery from MLE is possible. However, to the best of our knowledge, their tightness is not understood beyond this regime. As an illustrative example, we focus on the generalized Procrustes problem.	en_US
dc.language.iso	en_US	en_US
dc.relation.ispartof	Proceedings of The 27th Conference on Learning Theory	en_US
dc.rights	Author's manuscript	en_US
dc.title	Open problem: Tightness of maximum likelihood semidefinite relaxations	en_US
dc.type	Conference Article	en_US
dc.date.eissued	2014	en_US
pu.type.symplectic	http://www.symplectic.co.uk/publications/atom-terms/1.0/journal-article	en_US

Files in This Item:

File	Description	Size	Format
1404.2655v1.pdf		215.9 kB	Adobe PDF	View/Download