Mengdi Wang, Department of Operations Research and Financial Engineering, Princeton University (10:30am-11:30am, Thursday January 7, 2016) Room N510, Shunde Building 2016.01.08

【Time】10:30am-11:30am, Thursday January 7, 2016


【Venue】North 510, Shunde Building


【Title】Some Topics in Stochastic First-Order Methods and Beyond


【Speaker】Mengdi Wang, Department of Operations Research and Financial Engineering, Princeton University


【Host】Dr. Kaibo Wang

                   

【Abstract】We review some recent advances in stochastic gradient descent method and its variants, with an emphasis on data-intensive applications. More specifically, we discuss issues such as theoretical complexity and constraint randomization. We illustrate applications of SGD in statistical estimation and machine learning, and discuss some open theoretical questions. 


【Bio】Mengdi Wang is an assistant professor at Department of Operations Research and Financial Engineering, Princeton University. Mengdi Wang is interested in stochastic optimization that involves uncertainty or hidden information, with an emphasis on optimization in machine learning and dynamic programming.  


All interested are welcome!  

Department of Industrial Engineering, Tsinghua University
Phone: 010-62772989
Fax:010-62794399
E-mail:ieoffice@tsinghua.edu.cn
Address:Shunde Building, Tsinghua University, Beijing 100084


Copyright © 2014-2024 Department of Industrial Engineering, Tsinghua University