Quantum annealing for variational Bayes inference

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

研究成果: Paper査読

6 被引用数 (Scopus)

抄録

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).

本文言語English
ページ479-486
ページ数8
出版ステータスPublished - 2009 12 1
外部発表はい
イベント25th Conference on Uncertainty in Artificial Intelligence, UAI 2009 - Montreal, QC, Canada
継続期間: 2009 6 182009 6 21

Conference

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

ASJC Scopus subject areas

  • 人工知能
  • 応用数学

フィンガープリント

「Quantum annealing for variational Bayes inference」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル