Quantum annealing for variational Bayes inference

Issei Sato, Kenichi Kurihara, Shu Tanaka, Hiroshi Nakagawa, Seiji Miyashita

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

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).

Original languageEnglish
Title of host publicationProceedings of the 25th Conference on Uncertainty in Artificial Intelligence, UAI 2009
Pages479-486
Number of pages8
Publication statusPublished - 2009
Externally publishedYes
Event25th Conference on Uncertainty in Artificial Intelligence, UAI 2009 - Montreal, QC, Canada
Duration: 2009 Jun 182009 Jun 21

Other

Other25th Conference on Uncertainty in Artificial Intelligence, UAI 2009
CountryCanada
CityMontreal, QC
Period09/6/1809/6/21

Fingerprint

Variational Bayes
Annealing
Simulated annealing
Simulated Annealing
Free energy
Dirichlet
Free Energy
Experiments
Experiment

ASJC Scopus subject areas

  • Artificial Intelligence
  • Applied Mathematics

Cite this

Sato, I., Kurihara, K., Tanaka, S., Nakagawa, H., & Miyashita, S. (2009). Quantum annealing for variational Bayes inference. In Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence, UAI 2009 (pp. 479-486)

Quantum annealing for variational Bayes inference. / Sato, Issei; Kurihara, Kenichi; Tanaka, Shu; Nakagawa, Hiroshi; Miyashita, Seiji.

Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence, UAI 2009. 2009. p. 479-486.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Sato, I, Kurihara, K, Tanaka, S, Nakagawa, H & Miyashita, S 2009, Quantum annealing for variational Bayes inference. in Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence, UAI 2009. pp. 479-486, 25th Conference on Uncertainty in Artificial Intelligence, UAI 2009, Montreal, QC, Canada, 09/6/18.
Sato I, Kurihara K, Tanaka S, Nakagawa H, Miyashita S. Quantum annealing for variational Bayes inference. In Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence, UAI 2009. 2009. p. 479-486
Sato, Issei ; Kurihara, Kenichi ; Tanaka, Shu ; Nakagawa, Hiroshi ; Miyashita, Seiji. / Quantum annealing for variational Bayes inference. Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence, UAI 2009. 2009. pp. 479-486
@inproceedings{e761dcd6e990489b937b5c043916402e,
title = "Quantum annealing for variational Bayes inference",
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).",
author = "Issei Sato and Kenichi Kurihara and Shu Tanaka and Hiroshi Nakagawa and Seiji Miyashita",
year = "2009",
language = "English",
pages = "479--486",
booktitle = "Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence, UAI 2009",

}

TY - GEN

T1 - Quantum annealing for variational Bayes inference

AU - Sato, Issei

AU - Kurihara, Kenichi

AU - Tanaka, Shu

AU - Nakagawa, Hiroshi

AU - Miyashita, Seiji

PY - 2009

Y1 - 2009

N2 - 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).

AB - 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).

UR - http://www.scopus.com/inward/record.url?scp=80053140580&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80053140580&partnerID=8YFLogxK

M3 - Conference contribution

SP - 479

EP - 486

BT - Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence, UAI 2009

ER -