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. 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.


  • September 2021: Two papers (1, 2) accepted to NeurIPS 2021.
  • September 2021: Mahbod Majid wins the Waterloo CPI Cybersecurity and Privacy Excellence Graduate Scholarship.
  • June 2021: Two papers posted on arXiv (1, 2).
  • May 2021: Nicholas Vadivelu receives the Jessie W.H. Zou Memorial Award.
  • May 2021: Incoming students Alex Bie and Matt Regehr awarded the Vector Scholarship in Artifical Intelligence.
  • May 2021: One paper accepted to ICML 2021.
  • March 2021: One paper posted on arXiv.
  • December 2020: One paper accepted to ALT 2021.
  • November 2020: One paper accepted to IEEE Transactions on Information Theory.
  • October 2020: Two papers posted on arXiv (1 , 2), code for the former available here.
  • September 2020: One paper accepted to SODA 2021.
  • September 2020: Three papers accepted to NeurIPS 2020: one as spotlight (1), two as posters (1, 2).
  • September 2020: A course on differential privacy is publicly available.
  • July 2020: Discovery Grant with Accelerator Supplement awarded by NSERC.
  • June 2020: New paper on arXiv, code available here.
  • May 2020: Two papers (1, 2) accepted to COLT 2020. One paper accepted to ICML 2020.
  • April 2020: Survey of differentially private statistics posted on arXiv.
  • April 2020: New paper on arXiv, code available here.
  • March 2020: Resources for Research Groups Grant awarded by Compute Canada (joint with Xi He).
  • February 2020: Four new papers on arXiv: 1, 2, 3, 4.

Recent Publications

Remember What You Want to Forget: Algorithms for Machine Unlearning

Enabling Fast Differentially Private SGD via Just-in-Time Compilation and Vectorization

PAPRIKA: Private Online False Discovery Rate Control

Improved Rates for Differentially Private Stochastic Convex Optimization with Heavy-Tailed Data

The Price of Tolerance in Distribution Testing


Le Salonneur


Gautam Kamath

Assistant Professor of Computer Science

Statistics, Machine Learning, Data Privacy, Robustness

Postdoctoral Researchers


Vikrant Singhal

Postdoctoral Fellow

Statistics, Machine Learning, Data Privacy

Graduate Researchers


Alex Bie

MMath Computer Science Student

Privacy, Fairness


Argyris Mouzakis

PhD Computer Science Student

Machine Learning Theory, Algorithmic Statistics, Privacy, Applied Probability


Christian Covington

MMath Computer Science Student

Statistical Validity, Data Privacy, Robustness


Mahbod Majid

MMath Computer Science Student

Private Statistics, Robust Statistics


Matthew Regehr

MMath Computer Science Student

Machine Learning, Privacy, Reinforcement Learning

Undergraduate Researchers


Jimmy Di

BMath in Computer Science Student

Machine Learning, Privacy, Robustness


Landy Xu

BMath Computer Science & Statistics student

Machine Learning, Data Privacy, Statistics, Programming


Nicholas Vadivelu

BMath Computer Science & Statistics Student

Machine Learning, Statistics, Programming Languages


Sourav Biswas

BMath Computer Science & BBA Finance Student

Statistics, Machine Learning, Computer Vision, Data Privacy


Xingtu Liu

BMath Student

Deep Learning Theory, Machine Learning, Statistics, Optimization

Affiliated Researchers


Linfeng Ye

MEng Electrical and Computer Engineering student

Computer Vision, Optimization, Machine Learning


Pranav Subramani

MMath Data Science Student

Probabilistic Programming, Bayesian Inference, Differential Privacy, Adversarial Robustness


Shubhankar Mohapatra

PhD Computer Science Student

Data Privacy, Machine Learning, Federated Learning, Data Cleaning