| 電子情報通信学会 研究会発表申込システム 講演論文 詳細 |
技報閲覧サービス [ログイン] 技報アーカイブ |
| トップに戻る | 前のページに戻る | [Japanese] / [English] |
| 講演抄録／キーワード | ||
| 講演名 | 2010-11-04 15:00 ［ポスター講演］ブレグマン距離を用いた密度比推定の統一的枠組み ○杉山 将（東工大）・鈴木大慈（東大）・金森敬文（名大）  IBISML2010-64 |
|
| 抄録 | （和） | (事前公開アブストラクト) Estimation of the ratio of probability densities has attracted a great deal of attention since it can be used for addressing various statistical paradigms such as non-stationarity adaptation, two-sample test, outlier detection, mutual information estimation, dimensionality reduction, independent component analysis, causal inference, conditional density estimation, and probabilistic classification. A naive approach to density ratio approximation is to first estimates numerator and denominator densities separately and then take their ratio. However, this two-step approach does not perform well in practice, and methods for directly estimating the density ratio without going through density estimation have been explored, including methods based on moment matching, probabilistic classification, density matching, and density-ratio fitting. The contributions of this paper are three folds: First, we give a comprehensive review of existing density ratio estimation methods and discuss their pros and cons. The second contribution is that we propose a new framework of density ratio estimation in which a density-ratio model is fitted to the true density-ratio under the Bregman divergence. Our new framework includes all the above existing approaches as special cases, and is substantially more general. Thus, it provides a unified view of various density ratio estimation methods. Finally, we develop a robust density ratio estimation method under the power divergence, which is a novel instance in our framework. |
| （英） | Estimation of the ratio of probability densities has attracted a great deal of attention since it can be used for addressing various statistical paradigms such as non-stationarity adaptation, two-sample test, outlier detection, mutual information estimation, dimensionality reduction, independent component analysis, causal inference, conditional density estimation, and probabilistic classification. A naive approach to density ratio approximation is to first estimates numerator and denominator densities separately and then take their ratio. However, this two-step approach does not perform well in practice, and methods for directly estimating the density ratio without going through density estimation have been explored, including methods based on moment matching, probabilistic classification, density matching, and density-ratio fitting. The contributions of this paper are three folds: First, we give a comprehensive review of existing density ratio estimation methods and discuss their pros and cons. The second contribution is that we propose a new framework of density ratio estimation in which a density-ratio model is fitted to the true density-ratio under the Bregman divergence. Our new framework includes all the above existing approaches as special cases, and is substantially more general. Thus, it provides a unified view of various density ratio estimation methods. Finally, we develop a robust density ratio estimation method under the power divergence, which is a novel instance in our framework. |
|
| キーワード | （和） | / / / / / / / |
| （英） | density ratio / Bregman divergence / logistic regression / kernel mean matching / Kullback-Leibler importance estimation procedure / least-squares importance fitting / / | |
| 文献情報 | 信学技報, vol. 110, no. 265, IBISML2010-64, pp. 33-44, 2010年11月. | |
| 資料番号 | IBISML2010-64 | |
| 発行日 | 2010-10-28 (IBISML) | |
| ISSN | Print edition: ISSN 0913-5685 Online edition: ISSN 2432-6380 | |
| 著作権に ついて |
技術研究報告に掲載された論文の著作権は電子情報通信学会に帰属します．(許諾番号：10GA0019/12GB0052/13GB0056/17GB0034/18GB0034) | |
| PDFダウンロード | IBISML2010-64 |
|
| 研究会情報 | |
| 研究会 | IBISML |
| 開催期間 | 2010-11-04 - 2010-11-06 |
| 開催地（和） | 東大生産研 |
| 開催地（英） | IIS, Univ. of Tokyo |
| テーマ（和） | IBIS 2010 (情報論的学習理論ワークショップ) |
| テーマ（英） | IBIS 2010 (Workshop on Information-based Induction Sciences) |
| 講演論文情報の詳細 | |
| 申込み研究会 | IBISML |
| 会議コード | 2010-11-IBISML |
| 本文の言語 | 英語（日本語タイトルあり） |
| タイトル（和） | ブレグマン距離を用いた密度比推定の統一的枠組み |
| サブタイトル（和） | |
| タイトル（英） | A Unified Framework of Density Ratio Estimation under Bregman Divergence |
| サブタイトル（英） | |
| キーワード(1)（和/英） | / density ratio |
| キーワード(2)（和/英） | / Bregman divergence |
| キーワード(3)（和/英） | / logistic regression |
| キーワード(4)（和/英） | / kernel mean matching |
| キーワード(5)（和/英） | / Kullback-Leibler importance estimation procedure |
| キーワード(6)（和/英） | / least-squares importance fitting |
| キーワード(7)（和/英） | / |
| キーワード(8)（和/英） | / |
| 第1著者 氏名（和/英/ヨミ） | 杉山 将 / Masashi Sugiyama / スギヤマ マサシ |
| 第1著者 所属（和/英） | 東京工業大学 (略称： 東工大) Tokyo Institute of Technology (略称： Tokyo Inst. of Tech.) |
| 第2著者 氏名（和/英/ヨミ） | 鈴木 大慈 / Taiji Suzuki / スズキ タイジ |
| 第2著者 所属（和/英） | 東京大学 (略称： 東大) University of Tokyo (略称： Univ. of Tokyo) |
| 第3著者 氏名（和/英/ヨミ） | 金森 敬文 / Takafumi Kanamori / |
| 第3著者 所属（和/英） | 名古屋大学 (略称： 名大) Nagoya University (略称： Nagoya Univ.) |
| 講演者 | 第1著者 |
| 発表日時 | 2010-11-04 15:00:00 |
| 発表時間 | 180分 |
| 申込先研究会 | IBISML |
| 資料番号 | IBISML2010-64 |
| 巻番号（vol） | vol.110 |
| 号番号（no） | no.265 |
| ページ範囲 | pp.33-44 |
| ページ数 | 12 |
| 発行日 | 2010-10-28 (IBISML) |
[研究会発表申込システムのトップページに戻る]