Sparse Bayesian Hierarchical Mixture of Experts and Variational Inference

研究成果: Conference contribution

1 被引用数 (Scopus)

抄録

The hierarchical mixture of experts (HME) is a tree-structured probabilistic model for regression and classification. The HME has a considerable expression capability, however, the estimation of the parameters tends to overfit due to the complexity of the model. To avoid this problem, regularization techniques are widely used. In particular, it is known that a sparse solution can be obtained by L1 regularization. From a Bayesian point of view, regularization techniques are equivalent to assume that the parameters follow prior distributions and find the maximum a posteriori probability estimator. It is known that L1 regularization is equivalent to assuming Laplace distributions as prior distributions. However, it is difficult to compute the posterior distribution if Laplace distributions are assumed. In this paper, we assume that the parameters of the HME follow hierarchical prior distributions which are equivalent to Laplace distribution to promote sparse solutions. We propose a Bayesian estimation algorithm based on the variational method. Finally, the proposed algorithm is evaluated by computer simulations.

本文言語English
ホスト出版物のタイトルProceedings of 2018 International Symposium on Information Theory and Its Applications, ISITA 2018
出版社Institute of Electrical and Electronics Engineers Inc.
ページ60-64
ページ数5
ISBN(電子版)9784885523182
DOI
出版ステータスPublished - 2019 3 8
イベント15th International Symposium on Information Theory and Its Applications, ISITA 2018 - Singapore, Singapore
継続期間: 2018 10 282018 10 31

出版物シリーズ

名前Proceedings of 2018 International Symposium on Information Theory and Its Applications, ISITA 2018

Conference

Conference15th International Symposium on Information Theory and Its Applications, ISITA 2018
国/地域Singapore
CitySingapore
Period18/10/2818/10/31

ASJC Scopus subject areas

  • コンピュータ サイエンスの応用
  • 情報システム

フィンガープリント

「Sparse Bayesian Hierarchical Mixture of Experts and Variational 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