{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/efficient-non-stationary-online-learning-by","title":"Efficient Non-stationary Online Learning by Wavelets with Applications to Online Distribution Shift Adaptation","arxiv_id":null,"date":"2024-07-21","proceeding":"Proceedings of the 41st International Conference on Machine Learning (ICML) 2024 7","authors":["Yu-Yang Qian","Peng Zhao","Yu-Jie Zhang","Masashi Sugiyama","Zhi-Hua Zhou"],"abstract":"Dynamic regret minimization offers a principled way for non-stationary online learning, where the algorithm's performance is evaluated against changing comparators. Prevailing methods often employ a two-layer online ensemble, consisting of a group of base learners with different configurations and a meta learner that combines their outputs. Given the evident computational overhead associated with two-layer algorithms, this paper investigates how to attain optimal dynamic regret without deploying a model ensemble. To this end, we introduce the notion of underlying dynamic regret, a specific form of the general dynamic regret that can encompass many applications of interest. We show that almost optimal dynamic regret can be obtained using a single-layer model alone. This is achieved by an adaptive restart equipped with wavelet detection, wherein a novel streaming wavelet operator is introduced to online update the wavelet coefficients via a carefully designed binary indexed tree. We apply our method to the online label shift adaptation problem, leading to new algorithms with optimal dynamic regret and significantly improved computation/storage efficiency compared to prior arts. Extensive experiments validate our proposal.","url_abs":"https://openreview.net/forum?id=KNedb3bQ4h","url_pdf":"https://openreview.net/pdf?id=KNedb3bQ4h","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"efficient-non-stationary-online-learning-by","repo_url":"https://github.com/ZinYY/StreamingWavelet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[{"method_slug":"base","method_name":"BASE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}