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

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)