Murat Erdogdu
Appointment
Canada CIFAR AI Chair
Pan-Canadian AI Strategy
About
Appointed Canada CIFAR AI Chair – 2018
Murat Erdogdu is a Canada CIFAR AI Chair at the Vector Institute and an assistant professor in the department of computer science and statistical sciences at the University of Toronto.
With a background in engineering and statistics, Erdogdu has a keen interest in theoretical machine learning, more specifically, design and analysis of optimization and sampling algorithms for machine learning models.
Awards
- Connaught New Researcher Award, 2019
- Best Teaching Assistant Award, Department of Statistics, Stanford University, 2012
Relevant Publications
- Li, M., & Erdogdu M. A. (2023). Riemannian Langevin algorithm for solving semidefinite programs. In Bernoulli. 29(4): 3093-3113.
- Ba, J., Erdogdu, M. A., Suzuki, T., Wang, Z., Wu, D., & Yang, G. (2022). High-dimensional asymptotics of feature learning: How one gradient step improves the representation. In Advances in Neural Information Processing Systems. 35:37932-37946.
- Balasubramanian, K., Chewi, S., Erdogdu, M.A., Salim, A. & Zhang, S.. (2022). Towards a Theory of Non-Log-Concave Sampling:First-Order Stationarity Guarantees for Langevin Monte Carlo. In Proceedings of 35th Conference on Learning Theory. 178:2896-2923
- Li, X., Wu, D., Mackey, L., & Erdogdu, M. A. (2019). Stochastic runge-kutta accelerates langevin monte carlo and beyond.