Quantum annealing for variational Bayes inference

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

Research output: Contribution to conferencePaper

5 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
Pages479-486
Number of pages8
Publication statusPublished - 2009 Dec 1
Event25th Conference on Uncertainty in Artificial Intelligence, UAI 2009 - Montreal, QC, Canada
Duration: 2009 Jun 182009 Jun 21

Conference

Conference25th Conference on Uncertainty in Artificial Intelligence, UAI 2009
CountryCanada
CityMontreal, QC
Period09/6/1809/6/21

ASJC Scopus subject areas

  • Artificial Intelligence
  • Applied Mathematics

Fingerprint Dive into the research topics of 'Quantum annealing for variational Bayes inference'. Together they form a unique fingerprint.

  • Cite this

    Sato, I., Kurihara, K., Tanaka, S., Nakagawa, H., & Miyashita, S. (2009). Quantum annealing for variational Bayes inference. 479-486. Paper presented at 25th Conference on Uncertainty in Artificial Intelligence, UAI 2009, Montreal, QC, Canada.