Murat Erdogdu

Murat Erdogdu is an Assistant Professor at the University of Toronto, jointly appointed in the Department of Computer Science and Department of Statistical Sciences. He is also a faculty member at the Vector Institute and holds the CIFAR Chair in Artificial Intelligence.

• PhD in Statistics, Stanford University (advised by Mohsen Bayati and Andrea Montanari)
• MSc in Computer Science, Stanford University
• BSc in Electrical Engineering and Mathematics, Bogazici University

His research focuses on machine learning theory, high-dimensional statistics, and optimization. He has contributed to understanding gradient-based algorithms, sampling methods, and feature learning in structured data.

Recent publications address problems in:

• Heavy-tailed sampling
• Mean-field Langevin dynamics
• Robust feature learning
• Minimax regression
• Stochastic optimization under infinite noise

Scientific Awards:

• CIFAR Chair in Artificial Intelligence
• ICLR 2023 Spotlight
• NeurIPS 2019 & 2021 Spotlights

He teaches graduate courses like STA 414/2104 (Statistical Methods for Machine Learning II) and STA 4273 (Modern Learning Theory), emphasizing probabilistic modeling and theoretical analysis.