Welcome to The Salon!

The Salon is a group dedicated to the study of Statistics, Algorithms, Learning, and OptimizatioN. It is led by Professor Gautam Kamath at the Cheriton School of Computer Science at the University of Waterloo. Its members are also affiliated with the Vector Institute. Current emphases of the group include enriching our understanding of data privacy and robustness in statistics and machine learning.

The name of The Salon is in reference to the French practice from the 17th and 18th centuries, a central venue for exchange of some of the most important ideas of the era.

News

July 2024: “Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining” recognized with an ICML 2024 Best Paper Award.
July 2024: “The Discrete Gaussian for Differential Privacy” recognized with the 2024 Caspar Bowden Award for Outstanding Research in Privacy Enhancing Technologies.
June 2024: Three new papers (1, 2, 3) on arXiv.
May 2024: Three papers (1, 2, 3) accepted to ICML 2024.
April 2024: New paper on arXiv.
February 2024: One paper accepted to SaTML 2024.
January 2024: Matthew Yang recognized as a Finalist for the CRA Outstanding Undergraduate Research Award.
December 2023: Two papers (1, 2) accepted to ALT 2024.
November 2023: New paper on arXiv.
September 2023: Two posters (1, 2) and one spotlight (1) accepted to NeurIPS 2023.
August 2023: Two papers (1, 2) accepted to TMLR, and one paper posted to arXiv.
July 2023: Gautam Kamath wins the Faculty of Math Golden Jubilee Research Excellence Award.
May 2023: Incoming student Jimmy Di awarded the Vector Scholarship in Artifical Intelligence.
April 2023: One paper accepted to ICML 2023, and one paper posted on arXiv.
April 2023: The Salon is now affiliated with the Vector Institute.
March 2023: Two papers (1, 2) posted on arXiv.
February 2023: Mahbod Majid awarded Faculty of Mathematics Graduate Research Excellence Award.
February 2023: One paper accepted to STOC 2023, and one paper posted on arXiv.
January 2023: One paper posted on arXiv.