资源分类
》 资源 》论文》On Sampling from the Gibbs Distribution with Random Maximum A-Posteriori Perturbations

On Sampling from the Gibbs Distribution with Random Maximum A-Posteriori Perturbations

2020-01-16 | |  57 |   40 |   0

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.

上一篇：Active Learning for Probabilistic Hypotheses Using the Maximum Gibbs Error Criterion

下一篇：On the Complexity and Approximation of Binary Evidence in Lifted Inference

用户评价
全部评价

热门资源

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • The Variational S...

    Unlike traditional images which do not offer in...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...