Azala

Representational Transfer Learning for Matrix Completion

Gorde:
Argitaratua izan da:arXiv.org (Dec 9, 2024), p. n/a
Egile nagusia: He, Yong
Beste egile batzuk: Li, Zeyu, Liu, Dong, Qin, Kangxiang, Xie, Jiahui
Argitaratua:
Cornell University Library, arXiv.org
Gaiak:
Knowledge management
Matrices (mathematics)
Target acquisition
Principal components analysis
Subspaces
Statistical analysis
Statistical inference
Knowledge representation
Sarrera elektronikoa:Citation/Abstract
Full text outside of ProQuest
Etiketak: Etiketa erantsi
Etiketarik gabe, Izan zaitez lehena erregistro honi etiketa jartzen!
Laburpena: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.
ISSN:2331-8422
Baliabidea:Engineering Database