Output Divergence Criterion for Active Learning in Collaborative Settings
スポンサーリンク
概要
- 論文の詳細を見る
We address the task of active learning for linear regression models in collaborative settings. The goal of active learning is to select training points that would allow accurate prediction of output values. We propose a new active learning criterion that is aimed at directly improving the accuracy of the output value estimation by analyzing the effect of the new training points on the estimates of the output values. The advantages of the proposed method are highlighted in collaborative settings, in which most of the data points are missing, and the number of training data points is much smaller than the number of the parameters of the model.
- 一般社団法人情報処理学会の論文
- 2009-12-11
著者
-
Masashi Sugiyama
Department Of Computer Science Tokyo Institute Of Technology
-
Neil Rubens
Graduate School Of Information Systems University Of Electro-communications
-
Rubens Neil
Department Of Computer Science Tokyo Institute Of Technology
関連論文
- Direct Density Ratio Estimation for Large-scale Covariate Shift Adaptation
- Model-agnostic active learning (特集 「ベイジアン・ネットワークと応用」および一般)
- Artist Agent A2: Stroke Painterly Rendering Based on Reinforcement Learning
- Canonical Dependency Analysis based on Squared-loss Mutual Information
- Word sequences for second language acquisition: technical report (思考と言語)
- Influence-based active learning for collaborative filtering (「プリファレンスモデリングと推薦システム」及び一般)
- Output Divergence Criterion for Active Learning in Collaborative Settings
- 1. Estimate Response-based Active Learning
- Recommending collaborative activities in informal learning using Bayesian methodology
- Output Divergence Criterion for Active Learning in Collaborative Settings
- Output divergence criterion for active learning in collaborative settings (数理モデル化と問題解決・バイオ情報学)