【海韵讲座】2023年第47期-pg娱乐电子游戏

 【海韵讲座】2023年第47期-pg娱乐电子游戏
86 592 2580110
【海韵讲座】2023年第47期-exploiting diversity for online learning with adaptivity and robustness
发布时间:2023年09月04日 17:15 点击:次

报告题目:exploiting diversity for online learning with adaptivity and robustness

主讲人: 卢琴 佐治亚大学 助理教授

报告时间:2023年09月8日(星期五)9:00-10:00

报告地点:线上 #腾讯会议:911-581-585

https://meeting.tencent.com/dm/1dqk9a9cnitx

报告摘要:

artificial intelligence (ai) has revolutionized every aspect of our daily life. a key algorithmic component underlying the recent ai-based applications is function approximation. in many safety-critical applications where uncertainty quantification of the point function estimate is called for, one would resort to the well-established bayesian nonparametric function learning framework — the gaussian process (gp). building on the gp-based paradigm, this talk will cover two related and complementary online learning tasks, namely, supervised prediction and bayesian (bandit) optimization. specifically, how to ensemble (e) a diversity of gp learners will be designed to endow adaptivity in these two online tasks. besides, the associated theoretical results will be presented to demonstrate the robustness of the egp-based approaches. lastly, empirical results on real datasets will be showcased to validate the merits of the proposed methods relative to existing baselines.

报告人简介:

dr. qin lu is an assistant professor with the school of electrical and computer engineering at the university of georgia. previously, she worked as a postdoctoral research associate with prof. georgios b. giannakis at the university of minnesota. before that, she received her phd and bs degrees from the university of connecticut (uconn) and university of electronic science and technology of china in 2018 and 2013, respectively. her research interests span the areas of machine learning, data science, signal processing, and communications. specifically, her current focus is on gaussian processes, bayesian optimization, active learning, meta learning, and spatio-temporal inference over graphs, with their applications in networked and autonomous systems. she was awarded summer fellowship and doctoral dissertation fellowship at uconn. she was also a recipient of the women of innovation award in collegian innovation and leadership by connecticut technology council in 2018.

邀请人:信息与通信工程系 万磊副教授

主讲人 卢琴 佐治亚大学 助理教授 主持人
时间 2023-09-08 09:00:00 报告题目
首作者 people
职称 联系电话
邮箱 研究方向
主讲人简介 地点 腾讯会议:911-581-585
https://meeting.tencent.com/dm/1dqk9a9cnitx
办公室 研究院
网站地图