Exploiting sparse markov and covariance structure in multiresolution models
Name
icml09_final.pdf
Size
421.56 KB
Format
Adobe PDF
Checksum (MD5)
30a41b92637b62904cfce578ebb634c3
Author(s)
Choi, Myung Jin
Chandrasekaran, Venkat
Willsky, Alan S.
Date Issued
June 2009
Journal
International Conference on Machine Learning (ICML) 2009 proceedings
Publisher
Association for Computing Machinery / ACM Digital Library
Citation
Choi, Myung Jin, Venkat Chandrasekaran, and Alan S. Willsky. “Exploiting Sparse Markov
and
Covariance Structure in Multiresolution Models.” Proceedings of the 26th Annual International Conference on Machine Learning - ICML ’09. Montreal, Quebec, Canada, 2009. 1-8. Copyright 2009
by the author(s)/owner(s).
Version
Final published version
Abstract
We consider Gaussian multiresolution (MR) models in which coarser, hidden variables serve to capture statistical dependencies among the finest scale variables. Tree-structured MR models have limited modeling capabilities, as variables at one scale are forced to be uncorrelated with each other conditioned on other scales. We propose a new class of Gaussian MR models that capture the residual correlations within each scale using sparse covariance structure. Our goal is to learn a tree-structured graphical model connecting variables across different scales, while at the same time learning sparse structure for the conditional covariance within each scale conditioned on other scales. This model leads to an efficient, new inference algorithm that is similar to multipole methods in computational physics.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Massachusetts Institute of Technology. Laboratory for Information and Decision Systems
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1145/1553374.1553397
