Murat A. Erdogdu


Postdoctoral Researcher
Microsoft Research - New England


1 Memorial Drive, Cambridge, MA 02142
erdogdu at cs.toronto dot edu
erdogdu.a at microsoft dot com

I am currently a postdoctoral researcher at Microsoft Research - New England. I will join the departments of Computer Science and Statistical Sciences at University of Toronto as an assistant professor, and Vector Institute as a member in 2018. 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. I have B.S. degrees in Electrical Engineering and Mathematics, both from Bogazici University.

Research Interests

  • Optimization: Efficient algorithms for machine learning problems

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

  • Machine Learning: Graphical models, message passing algorithms

Selected Papers

M.A. Erdogdu, Y. Deshpande, A. Montanari, Inference in Graphical Models via SDP Hierarchies, NIPS 2017
M.A. Erdogdu, M. Bayati, L.H. Dicker Scaled Least Squares Estimator for GLMs in Large-Scale Problems, NIPS 2016
M.A. Erdogdu, Newton-Stein Method: An optimization method for GLMs via Stein’s lemma, NIPS 2015
M.A. Erdogdu and A. Montanari, Convergence rates of sub-sampled Newton methods, NIPS 2015
M. Bayati, M.A. Erdogdu, A. Montanari, Estimating Lasso risk and noise level, NIPS 2013