Reexamining low rank matrix factorization for trace norm regularization

Trace norm regularization is a widely used approach for learning low rank matrices. A standard optimization strategy is based on formulating the problem as one of low rank matrix factorization which, however, leads to a non-convex problem. In practice this approach works well, and it is often comput...

وصف كامل

التفاصيل البيبلوغرافية

الحاوية / القاعدة:	Mathematics in Engineering
المؤلفون الرئيسيون:	Carlo Ciliberto, Massimiliano Pontil, Dimitrios Stamos
التنسيق:	مقال
اللغة:	الإنجليزية
منشور في:	AIMS Press 2023-08-01
الموضوعات:	collaborative filtering low rank matrix factorization trace norm regularization
الوصول للمادة أونلاين:	https://www.aimspress.com/article/doi/10.3934/mine.2023053?viewType=HTML