-
Do Large Language Models (Really) Need Statistical Foundations?
On October 10, 2025 at 11:00 am till 12:00 pm E18-304Weijie Su, University of Pennsylvania
-
Transformers Learn Generalizable Chain-of-Thought Reasoning via Gradient Descent
On October 3, 2025 at 11:00 am till 12:00 pm E18-304Yuejie Chi, Yale University
-
TBD
On September 19, 2025 at 11:00 am till 12:00 pm E18-304Benjamin Recht, University of California – Berkeley
-
TBD
On September 5, 2025 at 11:00 am till 12:00 pm E18-304Robert Nowak, University of Wisconsin-Madison
-
TAP free energy, spin glasses, and vibrational inference
On July 7, 2025Abstract: We consider the Sherrington-Kirkpatrick model of spin glasses with ferromagnetically biased couplings. For a specific choice of the couplings mean, the resulting Gibbs measure is equivalent to the Bayesian posterior for a high-dimensional estimation problem known as Z2 synchronization. Statistical physics suggests to compute the expectation with respect to this Gibbs measure (the posterior…
-
Topics in Information and Inference Seminar
On July 7, 2025This seminar consists of a series of lectures each followed by a period of informal discussion and social. The topics are at the nexus of information theory, inference, causality, estimation, and non-convex optimization. The lectures are intended to be tutorial in nature with the goal of learning about interesting and exciting topics rather than merely…
-
Fundamental statistical limits in causal inference
On May 9, 2025 at 11:00 am till 12:00 pm E18-304Sivaraman Balakrishnan, Carnegie Mellon University
-
Tractable Agreement Protocols
On May 2, 2025 at 11:00 am till 12:00 pm E18-304Aaron Roth, University of Pennsylvania
-
How should we do linear regression?
On April 25, 2025 at 11:00 am till 12:00 pm E18-304Richard Samworth, University of Cambridge