Scholar
Michael Menart
Google Scholar ID: U3Vwd3YAAAAJ
University of Toronto, Vector Institute
Citations & Impact
Citations
154
H-index
5
i10-index
3
Publications
10
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- Private Algorithms for Stochastic Saddle Points and Variational Inequalities: Beyond Euclidean Geometry, NeurIPS 2024
- Public-data Assisted Private Stochastic Optimization: Power and Limitations, NeurIPS 2024
- Differentially Private Non-Convex Optimization under the KL Condition with Optimal Rates, ALT 2024
- Differentially Private Algorithms for the Stochastic Saddle Point Problem with Optimal Rates for the Strong Gap, COLT 2023
- Faster Rates of Convergence to Stationary Points in Differentially Private Optimization, ICML 2023
- Differentially Private Generalized Linear Models Revisited, NeurIPS 2022
- Differentially private stochastic optimization: New results in convex and non-convex settings, NeurIPS 2021
Research Experience
- Currently a postdoc in the Department of Computer Science at The University of Toronto, hosted by Aleksander Nikolov and Nicolas Papernot. Also a postdoctoral affiliate with the Vector Institute.
Education
- Ph.D. from The Ohio State University, advised by Raef Bassily
Background
- His research focuses on expanding the theoretical foundations of machine learning. He is specifically interested in the design and analysis of machine learning and optimization algorithms which operate under algorithmic constraints, such as privacy, stability, and fairness. His work both characterizes the limits of private learning under such constraints and develops techniques for avoiding bottlenecks in trustworthy machine learning by leveraging insights from theory.
Miscellany
- He’s on the job market, feel free to reach out!
Co-authors