English

Large-Flip Importance Sampling

Computation 2012-06-26 v1 Artificial Intelligence

Abstract

We propose a new Monte Carlo algorithm for complex discrete distributions. The algorithm is motivated by the N-Fold Way, which is an ingenious event-driven MCMC sampler that avoids rejection moves at any specific state. The N-Fold Way can however get "trapped" in cycles. We surmount this problem by modifying the sampling process. This correction does introduce bias, but the bias is subsequently corrected with a carefully engineered importance sampler.

Keywords

Cite

@article{arxiv.1206.5239,
  title  = {Large-Flip Importance Sampling},
  author = {Firas Hamze and Nando de Freitas},
  journal= {arXiv preprint arXiv:1206.5239},
  year   = {2012}
}

Comments

Appears in Proceedings of the Twenty-Third Conference on Uncertainty in Artificial Intelligence (UAI2007)

R2 v1 2026-06-21T21:24:05.039Z