Presentation 2013-11-13
Learning Common Features of Parametrized Tasks
Ichiro TAKEUCHI, Tatsuya HONGO, Masashi SUGIYAMA, Shinichi NAKAJIMA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We introduce a novel formulation of multi-task learning (MTL) called parametric task learning (PTL) that can systematically handle infinitely many tasks parameterized by a continuous parameter. Our key finding is that, for a certain class of PTL problems, the path of optimal task-wise solutions can be represented as piecewise-linear functions of the continuous task parameter. Based on this fact, we employ a parametric programming technique to obtain the common shared representation across all the continuously parameterized tasks efficiently. We show that our PTL formulation is useful in various scenarios such as learning under non-stationarity, cost-sensitive learning, and quantile regression, and demonstrate the usefulness of the proposed method experimentally in these scenarios.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) multitask learning / parametric programming
Paper # IBISML2013-66
Date of Issue

Conference Information
Committee IBISML
Conference Date 2013/11/5(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Information-Based Induction Sciences and Machine Learning (IBISML)
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Learning Common Features of Parametrized Tasks
Sub Title (in English)
Keyword(1) multitask learning
Keyword(2) parametric programming
1st Author's Name Ichiro TAKEUCHI
1st Author's Affiliation Nagoya Institute of Technology()
2nd Author's Name Tatsuya HONGO
2nd Author's Affiliation Nagoya Institute of Technology
3rd Author's Name Masashi SUGIYAMA
3rd Author's Affiliation Tokyo Institute of Technology
4th Author's Name Shinichi NAKAJIMA
4th Author's Affiliation Nikon
Date 2013-11-13
Paper # IBISML2013-66
Volume (vol) vol.113
Number (no) 286
Page pp.pp.-
#Pages 8
Date of Issue