Murat A. Erdogdu


Ph.D. Candidate,
Department of Statistics,
Stanford University


Murat Anıl Erdoğdu
Sequoia Hall 206, Stanford, CA 94305
erdogdu ÃT stanford DÕT edu
erdogdu ÃT cs.stanford DÕT edu

I am currently a Ph.D. student at Department of Statistics at Stanford University jointly advised by Mohsen Bayati and Andrea Montanari. I have completed my M.S. degree in Computer Science Department at Stanford. I have B.S. degrees in Electrical Engineering and Mathematics, both from Bogazici University.

Research Interests

  • Optimization: Stochastic algorithms for machine learning problems

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

  • Applied probability: Randomized algorithms for statistical learning

Selected Papers

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