题目:When Statistics Meets Computing: A Few Interesting Problems and Challenges
报告人:Tony Cai(蔡天文)
报告时间:2023年11月1日14:00-16:00
地点:国际会议中心一楼
报告人简介:
Tony Cai
Department of Statistics and Data Science
The Wharton School
University of Pennsylvania
蔡天文(Tony Cai)现任美国宾法尼亚大学沃顿商学院 Daniel HSiberberg 讲席教授及统计与数据科学教授;宾法尼亚大学应用数学及计算科学教授;宾夕法尼亚大学医学院生物统计,流行病学及信息学系资深学者。2017-2020年任沃顿商学院副院长。2006年当选国际数理统计学会(IMS)会士。2008 年获得世界统计学考普斯奖(COPSS Presidents’Award),2017 年任泛华统计学会(ICSA)主席,2019 年获泛华统计学会杰出成就奖,2023 年当选国际数理统计学会(IMS)侯任主席并获美国统计学会 Noether 杰出学者奖。曾任国际统计学顶尖刊物统计年刊(Annals of Statistics)主编,及多个权威学术期刊的编委会成员。蔡教授的主要研究方向是大数据分析,包括机器学习、高维统计、大规模统计推断、统计决策论、函数数据分析、非参数函数估计、以及在基因组与金融工程的应用。他的研究得到美国国家科学基金会、美国国家卫生研究院、及沃顿商学院全球倡议基金的资助。他在 Annals of Statistics,Journal of the American Statistical Association,Journal of the Royal Statistical Society B,Biometrika,Probability and Related Fields等期刊发表论文200余篇。
报告摘要:
In the conventional statistical framework, a major goal is to develop optimal statistical procedures based on the sample size and statistical model. However, in many contemporary applications, non-statistical concerns such as privacy, communication, and computational constraints associated with the statistical procedures become crucial. This raises a fundamental question in data science: how can we make optimal statistical inference under these non-statistical constraints?
In this talk, we explore recent advances in optimal differentially private learning and distributed learning under communication constraints in a few specific settings. Our results demonstrate novel and interesting phenomena and suggest directions for further investigation.
上一条: 没有了 |
下一条: 没有了 |