AI Lunch Series - Miles Cranmer

  • AI Lunch Series - Miles Cranmer
    2021-05-05EDT12:00:00 ~ 2021-05-05EDT13:00:00
Not all computers/devices will add this event to your calendar automatically. A calendar event file named "jlab-calendar.ics" will be placed in your downloads location. Depending on how your device/computer is configured, you may have to locate this file and double click on it to add the event to your calendar. Event dates, times, and locations are subject to change. Event details will not be updated automatically once you add this event to your own calendar. It is recommended that you confirm details prior to the event by visiting The live JLab Event Calendar. If you need assistance contact

“Interpretable Machine Learning for Physics, using Symbolic Regression and Graph Neural Networks” Miles Cranmer (Princeton)

Abstract: “In this talk I will argue two points 1) Symbolic regression, a machine learning technique that fits data by iteratively searching the space of all possible analytic equations, should be a standard machine learning algorithm in physics. 2) Symbolic regression can be extended to high-dimensional spaces, such as to models for N-body simulations, using the method we have developed. To begin the talk, I will introduce symbolic regression (SR), which is a relatively old but underdeveloped technique. I will demonstrate our new high-performance open-source SR software PySR. I will then discuss our research contribution: a technique for extending SR to high-dimensional spaces by the use of a neural network. I will focus on Graph Neural Networks (GNNs), which are a physically motivated neural network architecture, and very relevant to many physical and astrophysical problems. As a validation, I will demonstrate that we can use this technique of a GNN to SR to extract the correct force laws and Hamiltonians from simple particle simulations. I will then show work applying our method to the Quijote dark matter simulations – where it finds a simple analytic formula to estimate the over-density of dark matter in a halo using learned metrics which summarize the nearby halos, giving a functional form that is more accurate than hand-derived formulas. Our approach simultaneously offers an interpretable ML technique for high-dimensional astrophysical data, and also a way of interpreting neural networks. (Demo code is available here)"

Join with Bluejeans:

Event Date
(AI) Artificial Intelligence
Scientific Program
Contact Name
Chris Tennant
(757) 240-7900