Skip to Content

Loading Events

The Power of Stagewise Learning

« All Events

  • This event has passed.

October 31 @ 3:30 pm - 4:20 pm

Professor Tianbao Yang, a computer science professor as the University of Iowa will present “The Power of Stagewise Learning: From Support Vector Machine to Generative Adversarial Nets”

 

ABSTRACT:
In the past decade, we have seen dramatic evolution of machine learning from convex methods to nonconvex methods and from shallow models to deep models. Lying at the heart of machine learning, mathematical optimization has played an important and indispensable role in solving many different learning problems. However, there is still a big gap between the practice used in deep learning community and the existing theory. In this talk, I will focus on a learning paradigm called stagewise learning that is different from conventional learning methods based on stochastic gradient descent with a continuously decreasing step size. I will show that the proposed stagewise learning algorithms can achieve significant improvements in both theory and practice over standard stochastic gradient method for solving many machine learning problems, including support vector machine, AUC optimization, deep neural networks and generative adversarial networks.

BIO:
Dr. Tianbao Yang received a PhD in computer science from Michigan State University in 2012. Before joining the University of Iowa, he was a researcher in NEC Laboratories America at Cupertino (2013-2014) and a Machine Learning Researcher in GE Global Research (2012-2013). Dr. Yang has board interests in machine learning and he has focused on several research topics, including large-scale optimization in machine learning, deep learning, and learning theory. His recent research focuses on developing efficient algorithms for solving challenging non-convex problems in machine learning. He has won the Best Paper Award at 25th Conference on Learning Theory (COLT) in 2012. He received the NSF Career Award in 2019.

 

Details

Date:
October 31
Time:
3:30 pm - 4:20 pm

Venue

3505 Seamans Center
Posted on October 28th, 2019

Site by Mark Root-Wiley of MRW Web Design