講演名 2014-11-18
Support Consistency of Direct Sparse-Change Learning in Markov Networks
,
PDFダウンロードページ PDFダウンロードページへ
抄録(和)
抄録(英) We study the problem of learning sparse structure changes between two Markov networks P and Q. Rather than fitting two Markov networks separately to two sets of data and figuring out their differences, a recent work proposed to learn changes directly via estimating the ratio between two Markov network models. Such a direct approach was demonstrated to perform excellently in experiments, although its theoretical properties remained unexplored. In this paper, we give sufficient conditions for successful change detection with respect to the sample size n_p, n_q, the dimension of data m, and the number of changed edges d. More specifically, we prove that the true sparse changes can be consistently identified for n_p=Ω(d^2 log(m^2+m)/2) and n_q=Ω(n^2_p/d), with an exponentially decaying upper-bound on learning error. Our theoretical guarantee can be applied to a wide range of discrete/continuous Markov networks.
キーワード(和)
キーワード(英) Density Ratio Estimation / Change Detection / Markov Network
資料番号 IBISML2014-70
発行日

研究会情報
研究会 IBISML
開催期間 2014/11/10(から1日開催)
開催地(和)
開催地(英)
テーマ(和)
テーマ(英)
委員長氏名(和)
委員長氏名(英)
副委員長氏名(和)
副委員長氏名(英)
幹事氏名(和)
幹事氏名(英)
幹事補佐氏名(和)
幹事補佐氏名(英)

講演論文情報詳細
申込み研究会 Information-Based Induction Sciences and Machine Learning (IBISML)
本文の言語 ENG
タイトル(和)
サブタイトル(和)
タイトル(英) Support Consistency of Direct Sparse-Change Learning in Markov Networks
サブタイトル(和)
キーワード(1)(和/英) / Density Ratio Estimation
第 1 著者 氏名(和/英) / Song LIU
第 1 著者 所属(和/英)
Department of Computer Science, Tokyo Institute of Technology
発表年月日 2014-11-18
資料番号 IBISML2014-70
巻番号(vol) vol.114
号番号(no) 306
ページ範囲 pp.-
ページ数 7
発行日