Gautam Kamath

Faculty Member

Assistant Professor, David R. Cheriton School of Computer Science, University of Waterloo

Canada CIFAR Artificial Intelligence Chair

Gautam Kamath is an Assistant Professor at the Cheriton School of Computer Science at the University of Waterloo. He is also a Faculty Member at the Vector Institute and a Canada CIFAR AI Chair. At Waterloo, he is further affiliated with Waterloo.AI and the Cybersecurity and Privacy Institute. His research interests are in reliable and trustworthy statistics and machine learning, particularly considerations such as privacy and robustness. He is an editor-in-chief of Transactions on Machine Learning Research (TMLR). He completed his B.S. at Cornell University, and his M.S. and Ph.D. at MIT. He also spent a year as a Microsoft Research Fellow at the Simons Institute for the Theory of Computing at UC Berkeley.

Research Interests

  • Privacy 
  • Robustness 
  • Statistics and Machine Learning

Highlights

  • University of Waterloo Faculty of Math Golden Jubilee Research Excellence Award
  • Canada CIFAR AI Chair in 2023
  • NSERC Discovery Accelerator Supplement 
  • Cornell University Computer Science Prize for Academic Excellence

Publications

The role of adaptive optimizers for honest private hyperparameter selection

Shubhankar Mohapatra and Sajin Sasy and Xi He and Gautam Kamath and Om Thakkar

2022

Robustness implies privacy in statistical estimation

Samuel B Hopkins and Gautam Kamath and Mahbod Majid and Shyam Narayanan

2023

Exploring the limits of model-targeted indiscriminate data poisoning attacks

Yiwei Lu and Gautam Kamath and Yaoliang Yu

2023

Private gans, revisited

Alex Bie and Gautam Kamath and Guojun Zhang

2023

Advancing differential privacy: Where we are now and future directions for real-world deployment

Rachel Cummings and Damien Desfontaines and David Evans and Roxana Geambasu and Yangsibo Huang and Matthew Jagielski and Peter Kairouz and Gautam Kamath and Sewoong Oh and Olga Ohrimenko and Nicolas Papernot and Ryan Rogers and Milan Shen and Shuang Song and Weijie Su and Andreas Terzis and Abhradeep Thakurta and Sergei Vassilvitskii and Yu-Xiang Wang and Li Xiong and Sergey Yekhanin and Da Yu and Huanyu Zhang and Wanrong Zhang

2024

Private distribution learning with public data: The view from sample compression

Shai Ben-David and Alex Bie and Clément L Canonne and Gautam Kamath and Vikrant Singhal

2023

Distribution learnability and robustness

Shai Ben-David and Alex Bie and Gautam Kamath and Tosca Lechner

2024

Indiscriminate Data Poisoning Attacks on Pre-trained Feature Extractors

Yiwei Lu and Matthew YR Yang and Gautam Kamath and Yaoliang Yu

2024

Not All Learnable Distribution Classes are Privately Learnable

Mark Bun and Gautam Kamath and Argyris Mouzakis and Vikrant Singhal

2024

Individual Privacy Accounting for Differentially Private Stochastic Gradient Descent

Da Yu and Gautam Kamath and Janardhan Kulkarni and Tie-Yan Liu and Jian Yin and Huishuai Zhang

2023

Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks

Jimmy Z. Di and Jack Douglas and Jayadev Acharya and Gautam Kamath and Ayush Sekhari

2023