ダウンロード数: 141
このアイテムのファイル:
ファイル | 記述 | サイズ | フォーマット | |
---|---|---|---|---|
1742-6596/699/1/012019.pdf | 1.45 MB | Adobe PDF | 見る/開く |
完全メタデータレコード
DCフィールド | 値 | 言語 |
---|---|---|
dc.contributor.author | Ohzeki, Masayuki | en |
dc.contributor.alternative | 大関, 真之 | ja |
dc.date.accessioned | 2017-03-14T01:02:38Z | - |
dc.date.available | 2017-03-14T01:02:38Z | - |
dc.date.issued | 2016-03 | - |
dc.identifier.issn | 1742-6596 | - |
dc.identifier.uri | http://hdl.handle.net/2433/218815 | - |
dc.description.abstract | We implement the simple method to accelerate the convergence speed to the steady state and enhance the mixing rate to the stochastic gradient Langevin method. The ordinary stochastic gradient method is based on mini-batch learning for reducing the computational cost when the amount of data is extraordinary large. The stochasticity of the gradient can be mitigated by the injection of Gaussian noise, which yields the stochastic Langevin gradient method; this method can be used for Bayesian posterior sampling. However, the performance of the stochastic Langevin gradient method depends on the mixing rate of the stochastic dynamics. In this study, we propose violating the detailed balance condition to enhance the mixing rate. Recent studies have revealed that violating the detailed balance condition accelerates the convergence to a stationary state and reduces the correlation time between the samplings. We implement this violation of the detailed balance condition in the stochastic gradient Langevin method and test our method for a simple model to demonstrate its performance. | en |
dc.format.mimetype | application/pdf | - |
dc.language.iso | eng | - |
dc.publisher | Institute of Physics Publishing | en |
dc.rights | © Published under licence by IOP Publishing Ltd. Content from this work may be used under the terms of the Creative Commons Attribution 3.0 licence. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI. | en |
dc.title | Stochastic gradient method with accelerated stochastic dynamics | en |
dc.type | conference paper | - |
dc.type.niitype | Conference Paper | - |
dc.identifier.jtitle | Journal of Physics: Conference Series | en |
dc.identifier.volume | 699 | - |
dc.relation.doi | 10.1088/1742-6596/699/1/012019 | - |
dc.textversion | publisher | - |
dc.identifier.artnum | 012019 | - |
dc.address | Department of Systems Science, Graduate School of Informatics, Kyoto University | en |
dcterms.accessRights | open access | - |
dcterms.alternative | International Meeting on High-Dimensional Data-Driven Science (HD3-2015) | en |
出現コレクション: | 学術雑誌掲載論文等 |
このリポジトリに保管されているアイテムはすべて著作権により保護されています。