Skip to main navigation Skip to search Skip to main content

Sample Complexity of Joint Structure Learning

  • Rensselaer Polytechnic Institute

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

Abstract

This paper considers the problem of jointly recovering the structures of two graphical models with unknown edge structures. It is assumed that both graphs have the same number of nodes and a known subset of nodes have identical structures in both graphs. The classes of Ising models and Gaussian models are considered. For Ising models, the objective is to recover the connectivity of both graphs under an approximate recovery criterion. For Gaussian models, the objectives of edge structure recovery and inverse covariance estimation are considered. Information-theoretic bounds on the sample complexity for bounded probability of error under the aforementioned criteria are established and compared with the corresponding bounds on the sample complexity for recovering the graphs independently.

Original languageEnglish
Title of host publication2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages5292-5296
Number of pages5
ISBN (Electronic)9781479981311
DOIs
StatePublished - May 2019
Event44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Brighton, United Kingdom
Duration: May 12 2019May 17 2019

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2019-May

Conference

Conference44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019
Country/TerritoryUnited Kingdom
CityBrighton
Period05/12/1905/17/19

Keywords

  • Graphical models
  • information-theoretic bounds
  • joint model selection
  • structural similarity

Fingerprint

Dive into the research topics of 'Sample Complexity of Joint Structure Learning'. Together they form a unique fingerprint.

Cite this