欢迎光临!
您现在所在的位置:首页 >> 通知公告 & 学术信息
科学研究
RESEARCH
Deep Representative Learning
时间  Datetime
2020-09-17 14:30 — 15:30
地点  Venue
Zoom APP()
报告人  Speaker
焦雨领
单位  Affiliation
武汉大学
邀请人  Host
统计系
备注  remarks
会议号:916 312 52307 会议密码:648620
报告摘要  Abstract

摘要: It is believe that success of deep learning depends on its automatic data representation abilities. But few theoretical works to explore this. In this talk, we present a statistical framework to achieva good data representation that enjoys information preservation, low dimensionality and disentanglement. At the population level, we formulate the ideal representation learning task as finding a nonlinearrepesentaion map that minimizes the sum of losses characterizing conditional independence and disentanglement. We estimate the target map at the sample level nonparametrically with deep neural networks. We derive a bound on the excess risk of the deep nonparametric estimator. The proposed method is validated via comprehensive numerical experiments and real data analysis in the context of regression and classification.


报告人简介:焦雨领,2014 年毕业于武汉大学数学与统计学院。主要从事统计计算、机器 学习、反问题等方面研究。主持国家自然科学基金面上项目、青年项目、湖北省自 然科学基金面上项目、统计与数据科学前沿理论及应用教育部重点实验室课题。 在包括 SIAM Journal on Numerical Analysis, SIAM Journal on Scientific Computing, Applied and Computational Harmonic Analysis, Statistical Science, Journal of Machine Learning Research, ICML, Inverse Problems, IEEE Transactions on Signal Processing, Statistica Sinica,中国科学等在内的期刊和会议上发表 30 余篇论文。