Conditional Density Estimation Based on Density Ratio Estimation

• Item type: SIG Technical Reports(1)
• 公開日: 2009-12-10
• タイトル: Conditional Density Estimation Based on Density Ratio Estimation
• タイトル / 言語: en
• タイトル: Conditional Density Estimation Based on Density Ratio Estimation
• 言語: eng
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_18gh
• 資源タイプ: technical report
• 著者所属: Tokyo Institute of Technology / Japan Science and Technology Agency
• 著者所属: Nagoya Institute of Technology
• 著者所属: The University of Tokyo
• 著者所属: Nagoya University
• 著者所属: Tokyo Institute of Technology
• 著者所属: The University of Tokyo
• 著者所属(英): en
• 著者所属(英): Tokyo Institute of Technology / Japan Science and Technology Agency
• 著者所属(英): en
• 著者所属(英): Nagoya Institute of Technology
• 著者所属(英): en
• 著者所属(英): The University of Tokyo
• 著者所属(英): en
• 著者所属(英): Nagoya University
• 著者所属(英): en
• 著者所属(英): Tokyo Institute of Technology
• 著者所属(英): en
• 著者所属(英): The University of Tokyo
• 著者名: Masashi, Sugiyama; Ichiro, Takeuchi; Taiji, Suzuki; Takafumi, Kanamori; Hirotaka, Hachiya; Daisuke, Okanohara
• 著者名(英): Masashi, Sugiyama; Ichiro, Takeuchi; Taiji, Suzuki; Takafumi, Kanamori; Hirotaka, Hachiya; Daisuke, Okanohara
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: Estimating the conditional mean of an input-output relation is the goal of regression. However, regression analysis is not sufficiently informative if the conditional distribution has multi-modality, is highly asymmetric, or contains heteroscedastic noise. In such scenarios, estimating the conditional distribution itself would be more useful. In this paper, we propose a novel method of conditional density estimation that is suitable for multi-dimensional continuous variables. The basic idea of the proposed method is to express the conditional density in terms of the density ratio and the ratio is directly estimated without going through density estimation.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: Estimating the conditional mean of an input-output relation is the goal of regression. However, regression analysis is not sufficiently informative if the conditional distribution has multi-modality, is highly asymmetric, or contains heteroscedastic noise. In such scenarios, estimating the conditional distribution itself would be more useful. In this paper, we propose a novel method of conditional density estimation that is suitable for multi-dimensional continuous variables. The basic idea of the proposed method is to express the conditional density in terms of the density ratio and the ratio is directly estimated without going through density estimation.
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AA12055912
• 書誌情報: 研究報告バイオ情報学（BIO）; 巻 2009-BIO-19, 号 4, p. 1-8, 発行日 2009-12-10
• Notice: SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc.
• 出版者 / 言語: ja
• 出版者: 情報処理学会