Hardness of Parameter Estimation in Graphical Models
Author(s)
Bresler, Guy; Gamarnik, David; Shah, Devavrat![Thumbnail](/bitstream/handle/1721.1/101045/Shah_Hardness%20of.pdf.jpg?sequence=4&isAllowed=y)
DownloadShah_Hardness of.pdf (353.5Kb)
PUBLISHER_POLICY
Publisher Policy
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.
Terms of use
Metadata
Show full item recordAbstract
We consider the problem of learning the canonical parameters specifying an undirected graphical model (Markov random field) from the mean parameters. For graphical models representing a minimal exponential family, the canonical parameters are uniquely determined by the mean parameters, so the problem is feasible in principle. The goal of this paper is to investigate the computational feasibility of this statistical task. Our main result shows that parameter estimation is in general intractable: no algorithm can learn the canonical parameters of a generic pair-wise binary graphical model from the mean parameters in time bounded by a polynomial in the number of variables (unless RP = NP). Indeed, such a result has been believed to be true (see the monograph by Wainwright and Jordan) but no proof was known. Our proof gives a polynomial time reduction from approximating the partition function of the hard-core model, known to be hard, to learning approximate parameters. Our reduction entails showing that the marginal polytope boundary has an inherent repulsive property, which validates an optimization procedure over the polytope that does not use any knowledge of its structure (as required by the ellipsoid method and others).
Date issued
2014Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science; Massachusetts Institute of Technology. Laboratory for Information and Decision Systems; Sloan School of ManagementJournal
Advances in Neural Information Processing Systems (NIPS)
Publisher
Neural Information Processing Systems Foundation
Citation
Bresler, Guy, David Gamarnik, and Devavrat Shah. "Hardness of Parameter Estimation in Graphical Models." Advances in Neural Information Processing Systems 27 (NIPS 2014)
Version: Author's final manuscript
ISSN
1049-5258