About me
I am a postdoc in the Department of Computer Science at The University of Toronto, hosted by Aleksander Nikolov and Nicolas Papernot. I am also a postdoctoral affiliate with the Vector Institute. Previously, I obtained my PhD the Ohio State University, where I was fortunate to be advised by Raef Bassily.
My research focuses on expanding the theoretical foundations of machine learning. I am specifically interested in the design and analysis of machine learning and optimization algorithms which operate under algorithmic constraints, such as privacy, stability, and fairness. My work both characterizes the limits of private learning under such constraints and develops techniuqes for avoiding bottlenecks in trustworthy machine learning by leveraging insights from theory.
Publications
Private Algorithms for Stochastic Saddle Points and Variational Inequalities: Beyond Euclidean Geometry
Raef Bassily, Cristóbal Guzmán, Michael Menart
NeurIPS 2024
Public-data Assisted Private Stochastic Optimization: Power and Limitations
E Ullah, M Menart, R Bassily, C Guzmán, R Arora
NeurIPS 2024
Differentially Private Non-Convex Optimization under the KL Condition with Optimal Rates
M Menart, E Ullah, R Arora, R Bassily, C Guzmán
ALT 2024
Differentially Private Algorithms for the Stochastic Saddle Point Problem with Optimal Rates for the Strong Gap
R Bassily, C Guzmán, M Menart
COLT 2023
Faster Rates of Convergence to Stationary Points in Differentially Private Optimization
R Arora, R Bassily, T González, C Guzmán, M Menart, E Ullah
ICML 2023
Differentially Private Generalized Linear Models Revisited
Raman Arora, Raef Bassily, Cristóbal Guzmán, Michael Menart, Enayat Ullah
NeurIPS 2022
Differentially private stochastic optimization: New results in convex and non-convex settings
Raef Bassily, Cristóbal Guzmán, Michael Menart
NeurIPS 2021