On lp-hyperparameter Learning via Bilevel Nonsmooth Optimization

We propose a bilevel optimization strategy for selecting the best hyperparameter value for the nonsmooth $\ell_p$ regularizer with $0 [abs] [ pdf ][ bib ] &copy JMLR 2021. ( edit, beta )

Authors

• Takayuki Okuno
• Akiko Takeda The University of Tokyo RIKEN
• Akihiro Kawana
• Motokazu Watanabe

Keywords

No keywords are indexed for this paper.