BIDS Machine Learning and Science Forum — Optimal Transport and the Geometry of Collider Data

ML&Sci Forum

December 6, 2021
11:00am to 12:00pm
Virtual Participation

BIDS Machine Learning and Science Forum
Date: Monday, December 6, 2021
Time: 11:00 AM - 12:00 PM Pacific Time
Location: Hybrid Session: To participate remotely, use this Zoom link, or RSVP to bpnachman@lbl.gov to attend in-person in Calvin Hall (attendance limited to 15 people).

Optimal Transport and the Geometry of Collider Data

Speaker: Katy Craig and Nathaniel Craig, University of California, Santa Barbara (and currently on sabbatical at UCB)
Abstract: Collider experiments probe physics at the shortest distances by smashing protons together and measuring the debris produced by the collisions. However, it is challenging to infer the detailed short-distance physics from the distribution of debris measured by the detector. Over the past two years, the mathematical field of optimal transport has emerged as a promising tool for classifying collider events based on these distributions. In this talk, we will describe how optimal transport distances endow collider data with a geometric structure that can be used for ML-based event classification, and we will show how selecting optimal transport distances with good geometric properties can dramatically reduce computational effort.

The BIDS Machine Learning and Science Forum meets biweekly to discuss current applications across a wide variety of research domains in the physical sciences and beyond. Hosted by BIDS Affiliates Uroš Seljak (professor of Physics at UC Berkeley) and Ben Nachman (physicist at Lawrence Berkeley National Laboratory), these active sessions bring together domain scientists, statisticians, and computer scientists who are either developing state-of-the-art methods or are interested in applying these methods in their research.  To receive email notifications about upcoming meetings, or to request more information, please contact the organizers at berkeleymlforum@gmail.comAll interested members of the UC Berkeley and Berkeley Lab communities are welcome and encouraged to attend. 

Speaker(s)

Katy Craig

Assistant Professor of Mathematics, University of California, Santa Barbara

Katy Craig is an Assistant Professor of Mathematics at the University of California, Santa Barbara, currently on sabbatical at UC Berkeley. Her interests include nonlinear PDE, optimal transport, calculus of variations, and numerical analysis. 

Nathaniel Craig

Associate Professor of Physics, University of California, Santa Barbara

Nathaniel Craig is an Associate Professor of Physics at the University of California, Santa Barbara, currently on sabbatical at UC Berkeley. He specializes in high energy theoretical physics.