2026-03-11T06:56:00Z https://ipsj.ixsq.nii.ac.jp/oai

oai:ipsj.ixsq.nii.ac.jp:00066990 2025-01-22T00:45:31Z 1164:5352:5656:5934

Conditional Density Estimation Based on Density Ratio Estimation Conditional Density Estimation Based on Density Ratio Estimation Masashi, Sugiyama Ichiro, Takeuchi Taiji, Suzuki Takafumi, Kanamori Hirotaka, Hachiya Daisuke, Okanohara Masashi, Sugiyama Ichiro, Takeuchi Taiji, Suzuki Takafumi, Kanamori Hirotaka, Hachiya Daisuke, Okanohara 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. 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. technical report 情報処理学会 2009-12-10 application/pdf 研究報告バイオ情報学（BIO） 4 2009-BIO-19 1 8 AA12055912 https://ipsj.ixsq.nii.ac.jp/record/66990/files/IPSJ-BIO09019004.pdf eng