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 primarily limited to the geometric mixture or moment-averaged paths associated with the exponential family and KL divergence. We explore AIS using $q$-paths, which include the geometric path as a special case and are related to the homogeneous power mean, deformed exponential family, and $\alpha$-divergence.
- Publication:
-
arXiv e-prints
- Pub Date:
- December 2020
- DOI:
- 10.48550/arXiv.2012.07823
- arXiv:
- arXiv:2012.07823
- Bibcode:
- 2020arXiv201207823B
- Keywords:
-
- Computer Science - Machine Learning
- E-Print:
- NeurIPS Workshop on Deep Learning through Information Geometry (Best Paper Award)