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 learning under such constraints and develops techniuqes for avoiding bottlenecks in trustworthy machine learning by leveraging insights from theory.

I’m on the job market, feel free to reach out! CV

Publications

• On the Gradient Complexity of Private Optimization with Private Oracles.
  M. Menart, A. Nikolov (preprint)

• Private Rate-Constrained Optimization with Applications to Fair Learning.
  M. Yaghini, T. Cebere, M. Menart, A. Bellete, N. Papernot (ICLR 2026)

• Private Algorithms for Stochastic Saddle Points and Variational Inequalities: Beyond Euclidean Geometry.
  R. Bassily, C. Guzmán, M. 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.
  R. Arora, R. Bassily, C. Guzmán, M. Menart, E. Ullah. (NeurIPS 2022)

• Differentially private stochastic optimization: New results in convex and non-convex settings.
  R. Bassily, C. Guzmán, M. Menart. (NeurIPS 2021)