Exact and Approximate Sampling by Systematic Stochastic Search

We introduce adaptive sequential rejection sampling, an algorithm for generating exact samples from high-dimensional, discrete distributions, building on ideas from classical AI search. Just as systematic search algorithms like A* recursively build complete solutions from partial solutions, sequential rejection sampling recursively builds exact samples over high-dimensional spaces from exact samples over lower-dimensional subspaces. Our algorithm recovers widely-used particle filters as an approximate variant without adaptation, and a randomized version of depth first search with backtracking when applied to deterministic problems. In this paper, we present the mathematical and algorithmic underpinnings of our approach and measure its behavior on undirected and directed graphical models, obtaining exact and approximate samples in a range of situations.

[1]  Wang,et al.  Nonuniversal critical dynamics in Monte Carlo simulations. , 1987, Physical review letters.

[2]  Vibhav Gogate,et al.  SampleSearch: A Scheme that Searches for Consistent Samples , 2007, AISTATS.

[3]  A. Sokal,et al.  Generalization of the Fortuin-Kasteleyn-Swendsen-Wang representation and Monte Carlo algorithm. , 1988, Physical review. D, Particles and fields.

[4]  Mark Huber,et al.  A bounding chain for Swendsen‐Wang , 2003, Random Struct. Algorithms.

[5]  L. Tippett,et al.  Applied Statistics. A Journal of the Royal Statistical Society , 1952 .

[6]  Michael I. Jordan,et al.  Mean Field Theory for Sigmoid Belief Networks , 1996, J. Artif. Intell. Res..

[7]  William T. Freeman,et al.  Comparison of graph cuts with belief propagation for stereo, using identical MRF parameters , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[8]  Nando de Freitas,et al.  Hot Coupling: A Particle Approach to Inference and Normalization on Pairwise Undirected Graphs , 2005, NIPS.

[9]  Michael I. Jordan,et al.  An Introduction to Variational Methods for Graphical Models , 1999, Machine-mediated learning.

[10]  A. Childs,et al.  Exact sampling from nonattractive distributions using summary states. , 2000, Physical review. E, Statistical, nonlinear, and soft matter physics.

[11]  Martin J. Wainwright,et al.  A new class of upper bounds on the log partition function , 2002, IEEE Transactions on Information Theory.

[12]  P. Moral,et al.  Sequential Monte Carlo samplers , 2002, cond-mat/0212648.

[13]  J. Propp,et al.  Exact sampling with coupled Markov chains and applications to statistical mechanics , 1996 .

[14]  Dale Schuurmans,et al.  Regularized Greedy Importance Sampling , 2002, NIPS.

[15]  David L. Waltz,et al.  Generating Semantic Descriptions From Drawings of Scenes With Shadows , 1972 .

[16]  W. Freeman,et al.  Generalized Belief Propagation , 2000, NIPS.

[17]  Tommi S. Jaakkola,et al.  New Outer Bounds on the Marginal Polytope , 2007, NIPS.