Minimax rates for sparse signal detection under correlation
作者:
时间:2022-04-21
阅读量:335次
  • 演讲人: 高超(芝加哥大学统计系助理教授)
  • 时间:2022年04月30日 周六 10:00(北京时间)
  • 地点:腾讯会议 417-340-765(密码: 13579)
  • 主办单位:数学科学学院统计所

摘要:We fully characterize the nonasymptotic minimax separation rate for sparse signal detection in the Gaussian sequence model with p equicorrelated observations, generalizing a result of Collier, Comminges, and Tsybakov. As a consequence of the rate characterization, we find that strong correlation is a blessing, moderate correlation is a curse, and weak correlation is irrelevant. Moreover, the threshold correlation level yielding a blessing exhibits phase transitions at the \sqrt{p} and p-\sqrt{p} sparsity levels. We also establish the emergence of new phase transitions in the minimax separation rate with a subtle dependence on the correlation level. Additionally, we study group structured correlations and derive the minimax separation rate in a model including multiple random effects. The group structure turns out to fundamentally change the detection problem from the equicorrelated case and different phenomena appear in the separation rate. 

报告人简介:高超,芝加哥大学统计系助理教授。2010 年本科毕业于浙江大学数学科学学 院,2011 年和 2016 年先后在耶鲁大学获得统计学硕士和博士学位。2016 年入职芝加哥大 学统计系,担任助理教授。同时任国际知名期刊《Bernoulli》和《Electronic Journal of Statistics》 的副主编。高超教授的研究领域涵盖非参数和高维统计、网络分析、贝叶斯理论和稳健统计 等,在统计学和机器学习领域的国际著名期刊(Annals of Statistics,Biometrika,Statistical Science,Journal of Machine Learning Research,IEEE Transactions on Information Theory 等) 发表学术论文 40 余篇。 他于 2019 年获美国国家科学基金职业奖(National Science Foundation Career Award),2021 年获得国际数理统计学会 Tweedie 奖(IMS Tweedie Award), 2022 年获得斯隆研究奖 ( Sloan Research Fellowship )。( 个 人 主 页 : https://www.stat.uchicago.edu/~chaogao/)

联系人:庞天晓老师(txpang@zju.edu.cn) 


欢迎各位老师和同学参加!