Active Learning for Undirected Graphical Model Selection

Divyanshu Vats, Robert Nowak, Richard Baraniuk
; Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics, PMLR 33:958-967, 2014.

Abstract

This paper studies graphical model selection, i.e., the problem of estimating a graph of statistical relationships among a collection of random variables. Conventional graphical model selection algorithms are passive, i.e., they require all the measurements to have been collected before processing begins. We propose an active learning algorithm that uses junction tree representations to adapt future measurements based on the information gathered from prior measurements. We prove that, under certain conditions, our active learning algorithm requires fewer scalar measurements than any passive algorithm to reliably estimate a graph. A range of numerical results validate our theory and demonstrates the benefits of active learning.

Cite this Paper


BibTeX
@InProceedings{pmlr-v33-vats14b, title = {{Active Learning for Undirected Graphical Model Selection}}, author = {Divyanshu Vats and Robert Nowak and Richard Baraniuk}, pages = {958--967}, year = {2014}, editor = {Samuel Kaski and Jukka Corander}, volume = {33}, series = {Proceedings of Machine Learning Research}, address = {Reykjavik, Iceland}, month = {22--25 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v33/vats14b.pdf}, url = {http://proceedings.mlr.press/v33/vats14b.html}, abstract = {This paper studies graphical model selection, i.e., the problem of estimating a graph of statistical relationships among a collection of random variables. Conventional graphical model selection algorithms are passive, i.e., they require all the measurements to have been collected before processing begins. We propose an active learning algorithm that uses junction tree representations to adapt future measurements based on the information gathered from prior measurements. We prove that, under certain conditions, our active learning algorithm requires fewer scalar measurements than any passive algorithm to reliably estimate a graph. A range of numerical results validate our theory and demonstrates the benefits of active learning.} }
Endnote
%0 Conference Paper %T Active Learning for Undirected Graphical Model Selection %A Divyanshu Vats %A Robert Nowak %A Richard Baraniuk %B Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2014 %E Samuel Kaski %E Jukka Corander %F pmlr-v33-vats14b %I PMLR %J Proceedings of Machine Learning Research %P 958--967 %U http://proceedings.mlr.press %V 33 %W PMLR %X This paper studies graphical model selection, i.e., the problem of estimating a graph of statistical relationships among a collection of random variables. Conventional graphical model selection algorithms are passive, i.e., they require all the measurements to have been collected before processing begins. We propose an active learning algorithm that uses junction tree representations to adapt future measurements based on the information gathered from prior measurements. We prove that, under certain conditions, our active learning algorithm requires fewer scalar measurements than any passive algorithm to reliably estimate a graph. A range of numerical results validate our theory and demonstrates the benefits of active learning.
RIS
TY - CPAPER TI - Active Learning for Undirected Graphical Model Selection AU - Divyanshu Vats AU - Robert Nowak AU - Richard Baraniuk BT - Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics PY - 2014/04/02 DA - 2014/04/02 ED - Samuel Kaski ED - Jukka Corander ID - pmlr-v33-vats14b PB - PMLR SP - 958 DP - PMLR EP - 967 L1 - http://proceedings.mlr.press/v33/vats14b.pdf UR - http://proceedings.mlr.press/v33/vats14b.html AB - This paper studies graphical model selection, i.e., the problem of estimating a graph of statistical relationships among a collection of random variables. Conventional graphical model selection algorithms are passive, i.e., they require all the measurements to have been collected before processing begins. We propose an active learning algorithm that uses junction tree representations to adapt future measurements based on the information gathered from prior measurements. We prove that, under certain conditions, our active learning algorithm requires fewer scalar measurements than any passive algorithm to reliably estimate a graph. A range of numerical results validate our theory and demonstrates the benefits of active learning. ER -
APA
Vats, D., Nowak, R. & Baraniuk, R.. (2014). Active Learning for Undirected Graphical Model Selection. Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics, in PMLR 33:958-967

Related Material