{"type":"ScholarlyArticle","title":"Sample Efficient Decentralized Stochastic Frank-Wolfe Methods for Continuous DR-Submodular Maximization","authors":[{"name":"Hongchang Gao","slug":"hongchang-gao","given":"Hongchang","family":"Gao","affiliation":""},{"name":"Hanzi Xu","slug":"hanzi-xu","given":"Hanzi","family":"Xu","affiliation":""},{"name":"Slobodan Vucetic","slug":"slobodan-vucetic","given":"Slobodan","family":"Vucetic","affiliation":""}],"abstract":"Continuous DR-submodular maximization is an important machine learning problem, which covers numerous popular applications.  With the emergence of large-scale distributed data, developing efficient algorithms for the continuous DR-submodular maximization, such as the decentralized Frank-Wolfe method, became an important challenge. However, existing decentralized Frank-Wolfe methods for this kind of problem have the sample complexity of $\\mathcal{O}(1/\\epsilon^3)$, incurring a large computational overhead. In this paper, we propose two novel sample efficient decentralized Frank-Wolfe methods to address this challenge. Our theoretical results demonstrate that the sample complexity of the two proposed methods is $\\mathcal{O}(1/\\epsilon^2)$, which is better than $\\mathcal{O}(1/\\epsilon^3)$ of the existing methods. As far as we know, this is the first published result achieving such a favorable sample complexity. Extensive experimental results confirm the effectiveness of the proposed methods.","doi":"10.24963/ijcai.2021/482","url":"https://ijcai.org/proceedings/2021/482","pdf":"https://ijcai.org/proceedings/2021/0482.pdf","markdown":"https://ijcai.org/proceedings/2021/482.md","bibtex":"https://ijcai.org/proceedings/2021/bibtex/482","volume":{"slug":"2021","title":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2021","url":"https://ijcai.org/proceedings/2021/","year":2021,"location":"Montreal","dates":"19-27 August 2021","editors":"Prof. Zhi-Hua Zhou","isbn":"978-0-9992411-9-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2021"},"section":"Machine Learning Applications","track":"Main Track","number":482,"pages":{"first":3501,"last":3507},"keywords":["Machine Learning Applications: Big data; Scalability"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}