Year: 2023
CAM-Net Digest, Vol. 20 (2023), Iss. 11 : p. 5
Abstract
课程日期：2023年7月7日-15日
授课时间：7月7/8/9/12/13/14 14:30-17:30；7月15日 09:00-11:00
课时数：20课时
课程地点：理学院东北楼一楼报告厅(110)
授课老师：Prof. Yuhong Yang, University of Minnesota
【课程简介】
The minimax rate in machine learning is a theoretical concept that is used to analyze the performance of a learning algorithm in the worst-case scenario. It is the minimum possible rate at which the expected error of the algorithm converges uniformly to zero, as the number of training examples approaches infinity, and the worst-case distribution (specific to the learning algorithm) over the input examples is considered. The minimax rate can be thought of as an essential benchmark for the performance of any learning algorithm, regardless of how it is constructed. For example, if an algorithm's convergence rate is slower than the minimax rate, it is considered suboptimal and thus needs to be improved. In this course, we will learn the basic ideas and tools to derive the minimax rate of convergence in machine learning.
【报名流程及联系人】
1、报名及录取方式：点击此处提交报名申请，由组委会筛选报名学员确定正式学员，拟录取资助外地学员不超过40人（以研究生为主，青年教师、高年级本科生若干）。
2、报名截止日期：2023年6月23日，我们将在6月28日在天元数学中部中心官网公布录取名单并通过邮件通知录取学员。
3、学员待遇：天元数学中部中心为外地学员安排住宿，为非本校学生提供餐补（用餐地点为校内，盒饭或餐卡补贴形式），本校学生可旁听课程，无资助。
4、联系人：杨老师 tmcc@whu.edu.cn 027-68788932
You do not have full access to this article.
Already a Subscriber? Sign in as an individual or via your institution
Journal Article Details
Publisher Name: Global Science Press
Language: Multiple languages
DOI: https://doi.org/2023-CAM-21855
CAM-Net Digest, Vol. 20 (2023), Iss. 11 : p. 5
Published online: 2023-01
AMS Subject Headings: Global Science Press
Copyright: COPYRIGHT: © Global Science Press
Pages: 1