Work

On $\ell_p$-hyperparameter Learning via Bilevel Nonsmooth Optimization

Year: 2018

Type: preprint

Abstract: We propose a bilevel optimization strategy for selecting the best hyperparameter value for the nonsmooth $\ell_p$ regularizer with $0

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.1806.01520

Authors: Okuno, Takayuki, Takeda, Akiko, Kawana, Akihiro, Watanabe, Motokazu

Institutions: RIKEN, RIKEN Center for Advanced Intelligence Project, The University of Tokyo, Tokyo Institute of Technology

Language: English

Topic: Stochastic Gradient Optimization Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: Japan Society for the Promotion of Science, Exploratory Research for Advanced Technology

Awards: Development of nonlinear semidefinite optimization theory and application to machine learning, G5359460732, G6658699011, Developing efficient algorithms for nonconvex non smooth optimization and its application to machine learning

OpenAlex ID: W3201344201

Cites: 37

Cited by: 3

Related to: 10