{"type":"ScholarlyArticle","title":"Stability and Generalization for Randomized Coordinate Descent","authors":[{"name":"Puyu Wang","slug":"puyu-wang","given":"Puyu","family":"Wang","affiliation":""},{"name":"Liang Wu","slug":"liang-wu","given":"Liang","family":"Wu","affiliation":""},{"name":"Yunwen Lei","slug":"yunwen-lei","given":"Yunwen","family":"Lei","affiliation":""}],"abstract":"Randomized coordinate descent (RCD) is a popular optimization algorithm with wide applications in various machine learning problems, which motivates a lot of theoretical analysis on its convergence behavior. As a comparison, there is no work studying how the models trained by RCD would generalize to test examples. In this paper, we initialize the generalization analysis of RCD by leveraging the powerful tool of algorithmic stability. We establish argument stability bounds of RCD for both convex and strongly convex objectives, from which we develop optimal generalization bounds by showing how to early-stop the algorithm to tradeoff the estimation and optimization. Our analysis shows that RCD enjoys better stability as compared to stochastic gradient descent.","doi":"10.24963/ijcai.2021/427","url":"https://ijcai.org/proceedings/2021/427","pdf":"https://ijcai.org/proceedings/2021/0427.pdf","markdown":"https://ijcai.org/proceedings/2021/427.md","bibtex":"https://ijcai.org/proceedings/2021/bibtex/427","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","track":"Main Track","number":427,"pages":{"first":3104,"last":3110},"keywords":["Machine Learning: Online Learning","Machine Learning: Learning Theory"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}