11月17日 | 杨宇红: Minimax optimal learning: adaptivity, model compression and limitation

时间:2022-11-14浏览:22设置


时   间:2022年11月17日(周四) 9:00-10:30

地   点:线上,腾讯会议:738-3897-6027  线下:理科大楼A1716

题   目:Minimax optimal learning: adaptivity, model compression and limitation

报告人:杨宇红 教授 明尼苏达大学

主持人:张澍一 助理教授

主   办:统计学院

摘   要:

Minimax-rate optimality plays a foundational role in theory of statistical and machine leaning. Besides the identification of minimax-rates of convergence and optimal learning procedures for various learning scenarios, adaptive strategies have also been devised to work simultaneously well for multiple or even infinitely (countably or continuously) many possible scenarios that may describe the underlying distribution of the data. Going with the exciting successes of the modern regression learning tools are questions/concerns/doubts on sparsity, model compressibility, instability, robustness and reliability of the fancy automated algorithms.

In this talk, we will first present on minimax optimal adaptive estimations for high-dimensional regression learning under hard and soft sparsity setups, taking advantage of recent sharp sparse linear approximation bounds. An application on model compression in neural network learning will be given. Then we will address the question that how adaptive and powerful any learning procedure really can be. We show that every procedure, no matter how it is constructed, can only work well for a limited set of regression functions.


报告人简历:

杨宇红,1988年获中国科大数学学士,1993年获伊利诺伊大学统计硕士,1996年获得耶鲁大学统计学博士,即加入Iowa State University统计学任助理教授,2001年升为副教授。从2007年起为明尼苏达大学School of Statistics教授。

他在统计、机器学习、高维数据等方向建立了深入的理论和方法,2010年成为数理统计学会会士。

他担任或曾担任数家重要统计杂志副编(ASSOCIATE EDITOR),包括Annals of Statistics, Statistica Sinica, Annals of Institute of Statistical Mathematics, Statistical Survey, JSPI。

其研究兴趣包括高维数据分析理论,模型选择和组合,多臂老虎机问题(Multi-Arm Bandit),精准医学统计问题,预测等。他曾主持4项国家科研项目,包括NSF CAREER Award。其研究成果包括80余篇学术论文,其中18篇为单作者(single author)。这些论文发表在统计、机器学习、信息论、计量经济、预测、逼近论等领域顶尖刊物,包括Annals of Statistics, JASA, Biometrika, JRSSB, IEEE Transactions on Information Theory, Journal of Econometrics, Journal of Approximation Theory, Journal of Machine Learning Research, and International Journal of Forecasting。

他的研究成果在多个领域的应用有广泛的影响,Google Scholar 上有近六千次引用 。

杨教授已经给出约150个学术会议邀请报告和应邀学术讲座。他为学术杂志审稿超过300篇,也为美国、加拿大、以色列、荷兰、比利时、香港等国家或地区评审研究基金或终身教授数十项。


返回原图
/