Quantum Annealing for Variational Bayes Inference
Machine Learning
2014-08-12 v1 Machine Learning
Abstract
This paper presents studies on a deterministic annealing algorithm based on quantum annealing for variational Bayes (QAVB) inference, which can be seen as an extension of the simulated annealing for variational Bayes (SAVB) inference. QAVB is as easy as SAVB to implement. Experiments revealed QAVB finds a better local optimum than SAVB in terms of the variational free energy in latent Dirichlet allocation (LDA).
Cite
@article{arxiv.1408.2037,
title = {Quantum Annealing for Variational Bayes Inference},
author = {Issei Sato and Kenichi Kurihara and Shu Tanaka and Hiroshi Nakagawa and Seiji Miyashita},
journal= {arXiv preprint arXiv:1408.2037},
year = {2014}
}
Comments
Appears in Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence (UAI2009)