IOE 899 Seminar Series: Andrew Gordon Wilson, Cornell University

Uncertainty, Loss Valleys, and Generalization in Deep Learning

The IOE 899 Seminar Series is open to all. U-M Industrial and Operations Engineering graduate students and faculty are especially encouraged to attend.

The seminar will be followed by a reception in the IOE Commons (Room 1709) from 4:00 pm-5:00 pm.

In this talk, we introduce a scalable Gaussian process framework capable of learning expressive kernel functions on large datasets, implemented in our new library GPyTorch. We then develop this framework into an approach for deep kernel learning, with full predictive distributions and automatic complexity calibration. We will consider applications in crime prediction, epidemiology, counterfactuals, and autonomous vehicles. We will also present our work in understanding loss geometry in deep learning, leading to practical training methods with scalable uncertainty representation and improved generalization.
Report Event As Inappropriate Contact Event Organizers

When and Where

Map Industrial and Operations Engineering Building - 1680

February 2019

 iCal  Google
3:00pm - 5:00pm

Explore Similar Events

  •  Loading Similar Events...