Murat Erdogdu

Murat A. Erdogdu is an Associate Professor in the Department of Computer Science and the Department of Statistical Sciences at the University of Toronto. He is affiliated with the Machine Learning Group, the Vector Institute, and holds a CIFAR Chair in Artificial Intelligence. His research focuses on machine learning theory, high-dimensional statistics, optimization, and sampling. He is also a faculty member of the Machine Learning Group and the Vector Institute.

Murat A. Erdogdu is a researcher at the University of Toronto with expertise in Machine Learning, Optimization, and Statistics. His work focuses on understanding the theoretical foundations of learning algorithms, particularly in high-dimensional settings. Erdogdu's research explores the convergence properties of optimization methods such as stochastic gradient descent and Langevin Monte Carlo, as well as their applications in statistical learning and neural networks. He investigates how data ordering and noise affect the performance of these algorithms, and how to improve their generalization capabilities. His studies also address the role of heavy-tailed distributions and the interplay between smoothness and tail growth in the convergence of optimization methods.