On sampling from the Gibbs distribution with random maximum a-posteriori perturbations
Name
Jaakkola_On sampling.pdf
Size
750.15 KB
Format
Adobe PDF
Checksum (MD5)
010dd189195f0fab2b6ec192c663c0bc
Author(s)
Hazan, Tamir
Maji, Subhransu
Jaakkola, Tommi S.
Date Issued
2013
Journal
Advances in Neural Information Processing Systems (NIPS)
Publisher
Neural Information Processing Systems
Citation
Hazan, Tamir, Subhransu Maji, and Tommi Jaakkola. "On sampling from the Gibbs distribution with random maximum a-posteriori perturbations." Advances in Neural Information Processing Systems 26 (NIPS 2013).
Version
Final published version
Abstract
In this paper we describe how MAP inference can be used to sample efficiently from Gibbs distributions. Specifically, we provide means for drawing either approximate or unbiased samples from Gibbs' distributions by introducing low dimensional perturbations and solving the corresponding MAP assignments. Our approach also leads to new ways to derive lower bounds on partition functions. We demonstrate empirically that our method excels in the typical high signal - high coupling'' regime. The setting results in ragged energy landscapes that are challenging for alternative approaches to sampling and/or lower bounds.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
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
http://papers.nips.cc/paper/4962-on-sampling-from-the-gibbs-distribution-with-random-maximum-a-posteriori-perturbations
