学术报告|
当前位置:首页 > 科研 > 学术报告
发表时间:2018-11-02 阅读次数:150次
报告题目: Learning from Dynamical Systems
报 告 人:杭汉源
报告人所在单位:中国人民大学
报告日期:2018-11-02 星期五
报告时间:14:30-15:30
报告地点:光华东主楼2001
  
报告摘要:

Supervised learning has always been attached great significance in the machine learning society where various algorithms are established commonly based on the assumption that data follow an i.i.d. distribution. In this manner, Empirical Risk Minimization usually serves as a beneficial theoretical framework for analysis on consistency, learning rates, etc. With the blossom of dynamical systems in a wide range of applications, focus now turns to the non-i.i.d. data. Here, we establish a new concentration inequality, namely a Bernstein-type inequality, that can be utilized as a powerful tool for learning on dynamical systems. When applying this inequality to support vector machines with Gaussian Kernels, we prove the consistency and also achieve almost optimal learning rates.

海报

  
本年度学院报告总序号:238

Copyright © |2012 复旦大学数学科学学院版权所有 沪ICP备042465  

电话:+86(21)65642341 传真:+86(21)65646073