Computational Science Seminar Series

Leveraging Physical Models in Machine Learning

by Prof. Rebecca Willett (University of Chicago)

US/Central
TCS (Bldg 240) Room 1416

TCS (Bldg 240) Room 1416

Argonne National Laboratory
Description

Locations: 

  • Attend in person at Argonne National Laboratory TCS (Bldg 240) Room 1416 
    [Visitors to ANL will need a gate pass - contact Rose Lynch (rlynch at anl.gov) no later than the morning of Dec 11]
     
  • Watch simulcast at Fermilab (Racetrack - WH7X) or
    UChicago (John Crerar Library, Kathleen A Zar Room, first floor)
     
  • Watch remotely with Bluejeans https://bluejeans.com/768600859 (see more info below)

Abstract: 

Machine learning, at its heart, is the process of learning from examples. However, in many scientific domains, we not only have training data or examples from which to learn, but also physical models of either the data collection mechanism or the underlying physical phenomenon. In this talk, I will describe two settings in which physical models can be incorporated within a machine learning framework to yield improved predictive performance. First, we will consider using training data to help solve ill-posed linear inverse problems such as deblurring, deconvolution, inpainting, compressed sensing, and superresolution. Recent advances in machine learning and image processing have illustrated that it is often possible to learn a regularizer from training data that can outperform more traditional regularizers. We will see that whether or how a forward model is leveraged can significantly impact how many training samples are needed to achieve a target accuracy. Second, we will examine using a combination of observational data and simulated data to improve subseasonal climate forecasts. Treating both types of data as co-equal training samples can bias many learning methods and yield misleading results. I will describe an alternative framework that combines observational data with a correlation graph that can be estimated from large ensemble climate model outputs, and we will see how this approach leads to more accurate forecasts. Finally, we will discuss open problems and future directions at the intersection of machine learning and the physical sciences.

Speaker Bio: Rebecca Willett is a Professor of Statistics and Computer Science at the University of Chicago. Her research interests include network and imaging science with applications in medical imaging, wireless sensor networks, astronomy, and social networks. Prof. Willett completed her PhD in Electrical and Computer Engineering at Rice University. Prior to joining the University of Chicago, she held the position of Assistant and Associate Professor in the Electrical and Computer Engineering department at Duke University and then the position of Associate professor in the Electrical and Computer Engineering department  at the University of Wisconsin-Madison. She has received several awards, including the National Science Foundation CAREER Award and the Air Force Office of Scientific Research Young Investigator Program award. She has also held visiting researcher positions at the Institute for Pure and Applied Mathematics at UCLA, the University of Wisconsin-Madison, the French National Institute for Research in Computer Science and Control (INRIA), and the Applied Science Research and Development Laboratory at GE Medical Systems (now GE Healthcare).

Remote Viewing Details:
https://bluejeans.com/768600859

Want to dial in from a phone?
Dial one of the following numbers:
+1.408.317.9254 (US (San Jose)
+1.866.226.4650 (US Toll Free)
(see all numbers - https://www.bluejeans.com/premium-numbers)

Enter the meeting ID 768600859 followed by #

Connecting from a room system?
Dial: bjn.vc or 199.48.152.152 and enter your meeting ID

Poster
Slides
Video
Questions? Contact Adam Lyon at