About me

I am a post-doc 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 characterizing the limits of differentially private optimization and machine learning. Other research interests include the role of stability in optimization and learning, the study of gradient oracle complexity lower bounds in first-order optimization methods, and bridging gaps between machine learning theory and practice.

Mike Menart

About me

Research

Private Algorithms for Stochastic Saddle Points and Variational Inequalities: Beyond Euclidean Geometry

Public-data Assisted Private Stochastic Optimization: Power and Limitations

Differentially Private Non-Convex Optimization under the KL Condition with Optimal Rates

Differentially Private Algorithms for the Stochastic Saddle Point Problem with Optimal Rates for the Strong Gap

Faster Rates of Convergence to Stationary Points in Differentially Private Optimization

Differentially Private Generalized Linear Models Revisited

Differentially private stochastic optimization: New results in convex and non-convex settings