Annealed Importance Sampling with Q-Paths

Abstract

Annealed importance sampling (AIS) is the gold standard for estimating partition functions or marginal likelihoods, corresponding to importance sampling over a path of distributions between a tractable base and an unnormalized target. While AIS yields an unbiased estimator for any path, existing literature has been limited to the geometric mixture or moment-averaged paths associated with the KL divergence and exponential family. We explore using $q$-paths for AIS, which are related to the homogeneous power means, deformed exponential family, and $\alpha$-divergence, and include the geometric path as a special case.

Cite

Text

Brekelmans et al. "Annealed Importance Sampling with Q-Paths." NeurIPS 2020 Workshops: DL-IG, 2020.

Markdown

[Brekelmans et al. "Annealed Importance Sampling with Q-Paths." NeurIPS 2020 Workshops: DL-IG, 2020.](https://mlanthology.org/neuripsw/2020/brekelmans2020neuripsw-annealed/)

BibTeX

@inproceedings{brekelmans2020neuripsw-annealed,
  title     = {{Annealed Importance Sampling with Q-Paths}},
  author    = {Brekelmans, Rob and Masrani, Vaden and Bui, Thang D and Wood, Frank and Galstyan, Aram and Steeg, Greg Ver and Nielsen, Frank},
  booktitle = {NeurIPS 2020 Workshops: DL-IG},
  year      = {2020},
  url       = {https://mlanthology.org/neuripsw/2020/brekelmans2020neuripsw-annealed/}
}