Subtle but not malicious? The (high) computational cost of non-smoothness in learning from big data

Subtle but not malicious? The (high) computational cost of non-smoothness in learning from big data

Neyman Seminar
May 3, 2017, 04:00 PM - 05:00 PM | 1011 Evans Hall | Happening As Scheduled
Mikhail Belkin, Department of Computer Science and Engineering, Ohio State University
What can we learn from big data? First, more data allows us to more precisely estimate probabilities of uncertain outcomes. Second, data provides better coverage to approximate functions more precisely. I will argue that the second is key to understanding the recent success of large scale machine learning. A useful way of thinking about this issue is that it is necessary to use many more...