{"type":"ScholarlyArticle","title":"Riemannian Stochastic Recursive Momentum Method for non-Convex Optimization","authors":[{"name":"Andi Han","slug":"andi-han","given":"Andi","family":"Han","affiliation":""},{"name":"Junbin Gao","slug":"junbin-gao","given":"Junbin","family":"Gao","affiliation":""}],"abstract":"We propose a stochastic recursive momentum method for Riemannian non-convex optimization that achieves a nearly-optimal complexity to find epsilon-approximate solution with one sample. The new algorithm requires one-sample gradient evaluations per iteration and does not require restarting with a large batch gradient, which is commonly used to obtain a faster rate. Extensive experiment results demonstrate the superiority of the proposed algorithm. Extensions to nonsmooth and constrained optimization settings are also discussed.","doi":"10.24963/ijcai.2021/345","url":"https://ijcai.org/proceedings/2021/345","pdf":"https://ijcai.org/proceedings/2021/0345.pdf","markdown":"https://ijcai.org/proceedings/2021/345.md","bibtex":"https://ijcai.org/proceedings/2021/bibtex/345","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":345,"pages":{"first":2505,"last":2511},"keywords":["Machine Learning: Online Learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}