On sampling from the Gibbs distribution with random maximum a-posteriori perturbations
Author(s)Hazan, Tamir; Maji, Subhransu; Jaakkola, Tommi S.
MetadataShow full item record
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.
DepartmentMassachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory; Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Advances in Neural Information Processing Systems (NIPS)
Neural Information Processing Systems
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).
Final published version