Murat A. Erdogdu

University of Toronto · Department of Computer Science · Department of Statistical Sciences Vector Institute Contact Pratt 286b, 6 King’s College Rd. Toronto, ON M5S 3G4 erdogdu at cs.toronto dot edu

I am an assistant professor at the University of Toronto in departments of Computer Science and Statistical Sciences. I am a faculty member of the Machine Learning Group and the Vector Institute, and a CIFAR Chair in Artificial Intelligence. Before, I was a postdoctoral researcher at Microsoft Research - New England. I did my Ph.D. at Department of Statistics at Stanford University where I was jointly advised by Mohsen Bayati and Andrea Montanari. I have an M.S. degree in Computer Science from Stanford, and B.S. degrees in Electrical Engineering and Mathematics, both from Bogazici University.

Research Interests

• Machine Learning: Theory for learning and sampling algorithms

• Optimization: Non-convex, convex algorithms for machine learning

• Statistics: High-dimensional data analysis, regularization and shrinkage

Some Recent Papers

• H. Wang, M. Gurbuzbalaban, L. Zhu, U. Simsekli and M.A. Erdogdu, Convergence Rates of Stochastic Gradient Descent under Infinite Noise Variance,  2021

• M. Li and M.A. Erdogdu, Riemannian Langevin Algorithm for Solving Semidefinite Programs,  2020

• L. Yu, K. Balasubramanian, S. Volgushev and M.A. Erdogdu, An Analysis of Constant Step Size SGD in the Non-convex Regime: Asymptotic Normality and Bias,  2020

• M.A. Erdogdu and R. Hosseinzadeh, On the Convergence of Langevin Monte Carlo: The Interplay between Tail Growth and Smoothness,  2020

• J. Ba, M.A. Erdogdu, T. Suzuki, D. Wu and T. Zhang, Generalization of Two-layer Neural Networks: An Asymptotic Viewpoint,  2020

• X. Li, D. Wu, L. Mackey and M.A. Erdogdu, Stochastic Runge-Kutta Accelerates Langevin Monte Carlo and Beyond,  2019

• A. Anastasiou, K. Balasubramanian and M.A. Erdogdu,  Normal Approximation for Stochastic Gradient Descent via Non-Asymptotic Rates of Martingale CLT,  2019