Quantum Annealing for Variational Bayes Inference

Issei Sato, Kenichi Kurihara, Shu Tanaka, Hiroshi Nakagawa, Seiji Miyashita
Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence, PMLR R7:487-494, 2009.

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 this Paper

BibTeX
@InProceedings{pmlr-vR7-sato09a, title = {Quantum Annealing for Variational {B}ayes Inference}, author = {Sato, Issei and Kurihara, Kenichi and Tanaka, Shu and Nakagawa, Hiroshi and Miyashita, Seiji}, booktitle = {Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence}, pages = {487--494}, year = {2009}, editor = {Bilmes, Jeff and Ng, Andrew Y.}, volume = {R7}, series = {Proceedings of Machine Learning Research}, month = {18--21 Jun}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r7/main/assets/sato09a/sato09a.pdf}, url = {https://proceedings.mlr.press/r7/sato09a.html}, 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).}, note = {Reissued by PMLR on 04 October 2026.} }
Endnote
%0 Conference Paper %T Quantum Annealing for Variational Bayes Inference %A Issei Sato %A Kenichi Kurihara %A Shu Tanaka %A Hiroshi Nakagawa %A Seiji Miyashita %B Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2009 %E Jeff Bilmes %E Andrew Y. Ng %F pmlr-vR7-sato09a %I PMLR %P 487--494 %U https://proceedings.mlr.press/r7/sato09a.html %V R7 %X 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). %Z Reissued by PMLR on 04 October 2026.
APA
Sato, I., Kurihara, K., Tanaka, S., Nakagawa, H. & Miyashita, S.. (2009). Quantum Annealing for Variational Bayes Inference. Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R7:487-494 Available from https://proceedings.mlr.press/r7/sato09a.html. Reissued by PMLR on 04 October 2026.

Related Material