Representational Transfer Learning for Matrix Completion

में बचाया:
ग्रंथसूची विवरण
में प्रकाशित:arXiv.org (Dec 9, 2024), p. n/a
मुख्य लेखक: He, Yong
अन्य लेखक: Li, Zeyu, Liu, Dong, Qin, Kangxiang, Xie, Jiahui
प्रकाशित:
Cornell University Library, arXiv.org
विषय:
ऑनलाइन पहुंच:Citation/Abstract
Full text outside of ProQuest
टैग: टैग जोड़ें
कोई टैग नहीं, इस रिकॉर्ड को टैग करने वाले पहले व्यक्ति बनें!
विवरण
सार: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.
आईएसएसएन:2331-8422
स्रोत:Engineering Database