- This event has passed.
LANS Seminar
Seminar Title: Toward physical generative models
Speaker: Nisha Chandramoorthy, Assistant Professor, Department of Statistics, University of Chicago.
Date: Thursday, April 9, 2026
Time: 2:30 PM-3:30 PM (In-Person)
Location: Hybrid, Bldg. 240, Conference Room 4301
Description: In any Generative Model, the generated samples have a different distribution than the data distribution, due to inevitable learning errors. Moreover, this discrepancy, and metrics for evaluating the generated samples, are hard to characterize in high dimensions, motivating the need to understand how learning errors affect the reproducibility of certain “features” of the generated distributions. A first question is whether generative models produce “physical” samples, i.e., samples whose support is close to that of the true target distribution, despite algorithmic errors. A second question concerns what we term a lazy generative model: given samples from the target, we apply an arbitrary random dynamical system such that the distribution at finite time is approximately Gaussian. In principle, this noising process cannot be exactly inverted to recover target samples—but under what conditions can we approximately recover samples from a nearby distribution? The first part is joint work with Adriaan de Clercq (UChicago) and the second with Georg Gottwald (U Sydney).
Bio: Nisha Chandramoorthy is an Assistant Professor in the Department of Statistics at the University of Chicago. She is part of the Committee of Computational and Applied Mathematics at UChicago and is affiliated with the NSF-Simons Institutes SkAI and NITMB. She works on the theory of machine learning and computational dynamical systems. She received her PhD from MIT in 2021.
Please note that the meeting URL for this event can be seen on the cels-seminars website which requires an Argonne login.
See all upcoming talks at https://www.anl.gov/mcs/lans-seminars