菠菜平台-十大菠菜平台

学术讲座

陈诉时间：2022年11月3日（周四）上午10:00

腾讯聚会会议：230-265-259

主讲人姓名：赵鹏，南京大学人工智能学院副研究员

主讲人简介： 赵鹏博士，南京大学人工智能学院副研究员。2021年于南京大学获博士学位。研究偏向为机械学习，主要包罗开放情况机械学习、稳健在线学习的理论与要领。研究结果发表在JMLR、COLT、ICML、NeurIPS等国际顶级学术期刊和聚会会议。曾担任多个学术期刊和聚会会议的审稿人或（高级）法式委员会成员，AAAI 2019组织委员会成员（流程主席）。

陈诉题目：Non-stationary Online Learning: An Online Ensemble Framework

陈诉摘要：Online learning is an important learning paradigm for dealing with sequential prediction and decision-making problems. The non-stationarity issue is a central challenge for modern online learning, given that many real-world data streams are collected in open environments and the distributions are naturally changing over time. In this talk, we will introduce our recent efforts on this topic. We introduce dynamic regret as the performance measure to guide the algorithm design, and then propose the online ensemble framework to optimize the measure. The framework can yield fruitful algorithmic and theoretical results for many important online learning problems and attain best-known or optimal guarantees.