Machine Learning / Artificial Intelligence Seminar - Andrew Gordon Wilson
September 15, 2026 10:00AM—11:00AM
Location:
In Person
-
Newell-Simon 3305
Speaker:
ANDREW GORDON WILSON,
Professor, Courant Institute of Mathematical Sciences and Center for Data ScienceNew York University, and Research Lead, Perplexity
https://cims.nyu.edu/~andrewgw/
Can we learn more from data than existed in the generating process itself? Can new and useful information be constructed from merely applying deterministic transformations to existing data? Can the learnable content in data be evaluated without considering a downstream task? On these questions, Shannon information and Kolmogorov complexity come up nearly empty-handed, in part because they assume observers with unlimited computational capacity and fail to target the useful information content. In this talk we identify and exemplify three seeming paradoxes in information theory: (1) information cannot be increased by deterministic transformations; (2) information is independent of the order of data; (3) likelihood modeling is merely distribution matching. To shed light on the tension between these results and modern practice, and to quantify the value of data, we introduce epiplexity, a formalization of information capturing what computationally bounded observers can learn from data. Epiplexity captures the structural content in data while excluding time-bounded entropy, the random unpredictable content exemplified by pseudorandom number generators and chaotic dynamical systems. With these concepts, we demonstrate how information can be created with computation, how it depends on the ordering of the data, and how likelihood modeling can produce more complex programs than present in the data generating process itself. We also present practical procedures to estimate epiplexity which we show capture differences across data sources, track with downstream performance, and highlight dataset interventions that improve out-of-distribution generalization. In contrast to principles of model selection, epiplexity provides a theoretical foundation for data selection, guiding how to select, generate, or transform data for learning systems.
—
Andrew Gordon Wilson is a Professor at the Courant Institute of Mathematical Sciences and Center for Data Science at New York University, and Research Lead at Perplexity. He aims to develop a prescriptive foundation for intelligent systems. His work includes generalization theory, Bayesian inference, equivariances, time-series forecasting, and scientific applications, particularly in computational biology, physics, and materials. He has received the NSF Career Award, the Heilbronn Distinguished Fellowship from the Isaac Newton Institute, the Amazon Research Award, and several best paper, test of time, dissertation, reviewer, and area chair awards. He has also been tutorial chair, workshop chair, and EXPO chair several times for ICML and NeurIPS, and is an ICML 2027 Program Chair.
Faculty Host: Nihar Shah
The AI-ML Seminar is generously sponsored by the MBZUAI/CMU Institute of Virtual and Programmable Cell
For More Information:
nihars@cs.cmu.edu