Southwest Jiaotong University School of Mathematics

统计系

首页  >  学术科研  >  统计系  >  正文

美国佐治亚大学统计系柯源博士学术报告

来源:   作者:统计系     日期:2019-06-17 11:25:39   点击数:  

报告题目: Measure the Generality of Convolutional Layers with Projection Correlation

报告地点:X2511

报告时间:20190701日周一上午10:30


This paper studies the transfer learning problem in image classification applications.
A phase transition phenomenon has been empirically validated: the convolutional layer shifts from general to specific with respect to the target task as its depth increases. The paper suggests measuring the generality of convolutional layers through an easy to compute and tuning free quantity named projection correlation. The non-asymptotic upper bounds for the estimation error of the proposed generality measure has been provided. Based on this generality measure, the paper proposes a forward adding layer selection algorithm to select generable layers. The algorithm aims to find a cut-off in the pre-trained model according to where the phase transition from general to specific happens. Then, we propose to transfer only the generable layers as specific layers can cause overfitting issues and hence hurt the prediction performance. The proposed algorithm is computationally efficient and can consistently estimate the true location of phase transition under mild conditions. Its superior empirical performance has been justified by various numerical experiments.


报告人简介:柯源博士, 美国佐治亚大学统计系助理教授,2015年获英国约克大学数学博士学位,美国普林斯顿大学博士后。研究领域包括高维统计推断,非参数、半参数模型, 金融计量学,因子模型分析,非线性时间序列分析,函数型数据分析,稳健统计方法等。柯教授已发表和已接受的SCI论文累计有8篇, 其中若干篇发表在统计学顶级期刊Annals of Statistics, Journal of American Statistical Association以及计量经济顶级期刊Journal of Econometrics 上。此外,柯教授还是很多顶级期刊和高水平期刊的审稿人。