Robust Group Synchronization via Quadratic Programming

Yunpeng Shi, Cole Wyeth, Gilad Lerman

Research output: Contribution to journalConference articlepeer-review

2 Scopus citations

Abstract

We propose a novel quadratic programming formulation for estimating the corruption levels in group synchronization, and use these estimates to solve this problem. Our objective function exploits the cycle consistency of the group and we thus refer to our method as detection and estimation of structural consistency (DESC). This general framework can be extended to other algebraic and geometric structures. Our formulation has the following advantages: it can tolerate corruption as high as the information-theoretic bound, it does not require a good initialization for the estimates of group elements, it has a simple interpretation, and under some mild conditions the global minimum of our objective function exactly recovers the corruption levels. We demonstrate the competitive accuracy of our approach on both synthetic and real data experiments of rotation averaging.

Original languageEnglish (US)
Pages (from-to)20095-20105
Number of pages11
JournalProceedings of Machine Learning Research
Volume162
StatePublished - 2022
Event39th International Conference on Machine Learning, ICML 2022 - Baltimore, United States
Duration: Jul 17 2022Jul 23 2022

Bibliographical note

Funding Information:
This work was supported by NSF awards 1821266, 2124913.

Publisher Copyright:
Copyright © 2022 by the author(s)

Fingerprint

Dive into the research topics of 'Robust Group Synchronization via Quadratic Programming'. Together they form a unique fingerprint.

Cite this