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...
मुख्य लेखकों: | , , |
---|---|
स्वरूप: | लेख |
भाषा: | English |
प्रकाशित: |
AIMS Press
2023-08-01
|
श्रृंखला: | Mathematics in Engineering |
विषय: | |
ऑनलाइन पहुंच: | https://www.aimspress.com/article/doi/10.3934/mine.2023053?viewType=HTML |