講演抄録/キーワード |
講演名 |
2014-11-17 17:00
[ポスター講演]Multitask learning meets tensor factorization: task imputation via convex optimization ○Kishan Wimalawarne(Tokyo Inst. of Tech.)・Masashi Sugiyama(Univ. of Tokyo)・Ryota Tomioka(TTIC) IBISML2014-49 |
抄録 |
(和) |
(事前公開アブストラクト) We study a multitask learning problem in which each task is parametrized by a weight vector and indexed by a pair of indices, which can be e.g, (consumer, time). The weight vectors can be collected into a tensor and the (multilinear-)rank of the tensor controls the amount of sharing of information among tasks. Two types of convex relaxations have recently been proposed for the tensor multilinear rank. However, we argue that both of them are not optimal in the context of multitask learning in which the dimensions or multilinear rank are typically inhomogeneous. We propose a new norm, which we call the scaled latent trace norm and analyze the excess risk of all the three norms. The results apply to various settings including matrix and tensor completion, multitask learning and multilinear multitask learning. Both the theory and experiments support the advantage of the new norm when the tensor is not equal-sized and we do not a priori know which mode is low rank. |
(英) |
We study a multitask learning problem in which each task is parametrized by a weight vector and indexed by a pair of indices, which can be e.g, (consumer, time). The weight vectors can be collected into a tensor and the (multilinear-)rank of the tensor controls the amount of sharing of information among tasks. Two types of convex relaxations have recently been proposed for the tensor multilinear rank. However, we argue that both of them are not optimal in the context of multitask learning in which the dimensions or multilinear rank are typically inhomogeneous. We propose a new norm, which we call the scaled latent trace norm and analyze the excess risk of all the three norms. Both the theory and experiments support the advantage of the new norm when the tensor is not equal-sized and we do not a priori know which mode is low rank. |
キーワード |
(和) |
/ / / / / / / |
(英) |
Multitask learning / scaled latent norm / tensor / / / / / |
文献情報 |
信学技報, vol. 114, no. 306, IBISML2014-49, pp. 111-118, 2014年11月. |
資料番号 |
IBISML2014-49 |
発行日 |
2014-11-10 (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 |
IBISML2014-49 |