Representational Transfer Learning for Matrix Completion

Guardado en:
书目详细资料
发表在:arXiv.org (Dec 9, 2024), p. n/a
主要作者: He, Yong
其他作者: Li, Zeyu, Liu, Dong, Qin, Kangxiang, Xie, Jiahui
出版:
Cornell University Library, arXiv.org
主题:
在线阅读:Citation/Abstract
Full text outside of ProQuest
标签: 添加标签
没有标签, 成为第一个标记此记录!

MARC

LEADER 00000nab a2200000uu 4500
001 3142734131
003 UK-CbPIL
022 |a 2331-8422 
035 |a 3142734131 
045 0 |b d20241209 
100 1 |a He, Yong 
245 1 |a Representational Transfer Learning for Matrix Completion 
260 |b Cornell University Library, arXiv.org  |c Dec 9, 2024 
513 |a Working Paper 
520 3 |a We propose to transfer representational knowledge from multiple sources to a target noisy matrix completion task by aggregating singular subspaces information. Under our representational similarity framework, we first integrate linear representation information by solving a two-way principal component analysis problem based on a properly debiased matrix-valued dataset. After acquiring better column and row representation estimators from the sources, the original high-dimensional target matrix completion problem is then transformed into a low-dimensional linear regression, of which the statistical efficiency is guaranteed. A variety of extensional arguments, including post-transfer statistical inference and robustness against negative transfer, are also discussed alongside. Finally, extensive simulation results and a number of real data cases are reported to support our claims. 
653 |a Knowledge management 
653 |a Matrices (mathematics) 
653 |a Target acquisition 
653 |a Principal components analysis 
653 |a Subspaces 
653 |a Statistical analysis 
653 |a Statistical inference 
653 |a Knowledge representation 
700 1 |a Li, Zeyu 
700 1 |a Liu, Dong 
700 1 |a Qin, Kangxiang 
700 1 |a Xie, Jiahui 
773 0 |t arXiv.org  |g (Dec 9, 2024), p. n/a 
786 0 |d ProQuest  |t Engineering Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3142734131/abstract/embedded/ZKJTFFSVAI7CB62C?source=fedsrch 
856 4 0 |3 Full text outside of ProQuest  |u http://arxiv.org/abs/2412.06233