Information Theory, Machine Learning and Statistics Seminar

Spring 2022

This term the Information Theory, Machine Learning and Statistics Seminar focuses on generalization
in machine learning, privacy and related topics. The seminar consists of a series of two-hours talks
aimed at graduate students and researchers with a basic knowledge of information theory and machine
learning. Talks are unusually long to allow speakers to discuss their results and proof techniques in detail.

Sessions take place every other Friday from 9am to 11am (CDT) over Zoom.
(Access link:

To be added to the seminar mailing list, please send an email to

List of Speakers

Date Speaker Title
25/Mar Tyler Sypherd
Arizona State University
Being properly improper
08/Apr Hrayr Harutyunyan
University of Southern California
Information-theoretic generalization bounds for black-box learning algorithms
22/Apr Shahab Asoodeh
McMaster University
06/May Wael Alghamdi
Harvard University
Schrodinger's cactus: optimal differential privacy mechanisms in the large-composition regime
20/May Shahab Asoodeh
McMaster University
Contraction coefficients of Markov kernels under local differential privacy

Previous Schedules
[Fall 2021] [Spring 2021] [Fall 2020]

Last update: May 3, 2022