
Contextual Symmetries in Probabilistic Graphical Models
An important approach for efficient inference in probabilistic graphical...
06/30/2016 ∙ by Ankit Anand, et al. ∙ 0 ∙ shareread it

Lifted Probabilistic Inference for Asymmetric Graphical Models
Lifted probabilistic inference algorithms have been successfully applied...
12/01/2014 ∙ by Guy Van den Broeck, et al. ∙ 0 ∙ shareread it

NonCount Symmetries in Boolean & MultiValued Prob. Graphical Models
Lifted inference algorithms commonly exploit symmetries in a probabilist...
07/27/2017 ∙ by Ankit Anand, et al. ∙ 0 ∙ shareread it

Partition MCMC for inference on acyclic digraphs
Acyclic digraphs are the underlying representation of Bayesian networks,...
04/20/2015 ∙ by Jack Kuipers, et al. ∙ 0 ∙ shareread it

Parallelizing MCMC with Random Partition Trees
The modern scale of data has brought new challenges to Bayesian inferenc...
06/10/2015 ∙ by Xiangyu Wang, et al. ∙ 0 ∙ shareread it

A Forest Mixture Bound for BlockFree Parallel Inference
Coordinate ascent variational inference is an important algorithm for in...
05/17/2018 ∙ by Neal Lawton, et al. ∙ 0 ∙ shareread it

Multicuts and Perturb & MAP for Probabilistic Graph Clustering
We present a probabilistic graphical model formulation for the graph clu...
01/09/2016 ∙ by Jörg Hendrik Kappes, et al. ∙ 0 ∙ shareread it
BlockValue Symmetries in Probabilistic Graphical Models
Several lifted inference algorithms for probabilistic graphical models first merge symmetric states into a single cluster (orbit) and then use these for downstream inference, via variations of orbital MCMC [Niepert, 2012]. These orbits are represented compactly using permutations over variables, and variablevalue (VV) pairs, but these can miss several state symmetries in a domain. We define the notion of permutations over blockvalue (BV) pairs, where a block is a set of variables. BV strictly generalizes VV symmetries, and can compute many more symmetries for increasing block sizes. To operationalize use of BV permutations in lifted inference, we describe 1) an algorithm to compute BV permutations given a block partition of the variables, 2) BVMCMC, an extension of orbital MCMC that can sample from BV orbits, and 3) a heuristic to suggest good block partitions. Our experiments show that BVMCMC can mix much faster compared to vanilla MCMC and orbital MCMC over VV permutations.
READ FULL TEXT