Murat A. Erdogdu

Faculty Member

Assistant Professor, Department of Computer Science and Department of Statistical Sciences, Faculty of Arts & Science, University of Toronto

Canada CIFAR Artificial Intelligence Chair

With a background in engineering, Murat has a keen interest in applying theory to solve real-world problems. His primary interest is in designing optimization algorithms for machine learning models. Using efficient algorithms, model training time can be reduced significantly, allowing researchers to efficiently test and select the best model for the problem at hand, be it recommender systems or image denoising. Murat completed his PhD in the Department of Statistics at Stanford University. He holds a Master’s in Computer Science from Stanford and Bachelor’s degrees in Electrical Engineering and Mathematics from Bogazici University in Turkey. Previously Murat was a postdoctoral researcher at Microsoft Research. Murat regularly publishes at the top-rated machine learning conference NIPS, and has journal papers in the Annals of Statistics and JMLR.

Publications

Convergence rate of block-coordinate maximization Burer–Monteiro method for solving large SDPs

Murat A Erdogdu and Asuman Ozdaglar and Pablo A Parrilo and Nuri Denizcan Vanli

2021

An analysis of constant step size sgd in the non-convex regime: Asymptotic normality and bias

Lu Yu and Krishnakumar Balasubramanian and Stanislav Volgushev and Murat A Erdogdu

2021

Convergence rates of stochastic gradient descent under infinite noise variance

Hongjian Wang and Mert Gurbuzbalaban and Lingjiong Zhu and Umut Simsekli and Murat A Erdogdu

2021

Manipulating sgd with data ordering attacks

Ilia Shumailov and Zakhar Shumaylov and Dmitry Kazhdan and Yiren Zhao and Nicolas Papernot and Murat A Erdogdu and Ross J Anderson

2021

Heavy tails in sgd and compressibility of overparametrized neural networks

Melih Barsbey and Milad Sefidgaran and Murat A Erdogdu and Gael Richard and Umut Simsekli

2021

Fractal structure and generalization properties of stochastic optimization algorithms

Alexander Camuto and George Deligiannidis and Murat A Erdogdu and Mert Gurbuzbalaban and Umut Simsekli and Lingjiong Zhu

2021

Understanding the Variance Collapse of SVGD in High Dimensions

Jimmy Ba and Murat A Erdogdu and Marzyeh Ghassemi and Shengyang Sun and Taiji Suzuki and Denny Wu and Tianzong Zhang

2021

Mirror Descent Strikes Again: Optimal Stochastic Convex Optimization under Infinite Noise Variance

Nuri Mert Vural and Lu Yu and Krishnakumar Balasubramanian and Stanislav Volgushev and Murat A Erdogdu

2022

On Empirical Risk Minimization with Dependent and Heavy-Tailed Data

Abhishek Roy and Krishnakumar Balasubramanian and Murat A Erdogdu

2021

Convergence and Optimality of Policy Gradient Methods in Weakly Smooth Settings

Matthew Shunshi Zhang and Murat Erdogdu and Animesh Garg

2022

Riemannian langevin algorithm for solving semidefinite programs

Mufan Li and Murat A Erdogdu

2023

Towards a complete analysis of langevin monte carlo: Beyond poincaré inequality

Alireza Mousavi-Hosseini and Tyler K Farghly and Ye He and Krishna Balasubramanian and Murat A Erdogdu

2023

An analysis of Transformed Unadjusted Langevin Algorithm for Heavy-tailed Sampling

Ye He and Krishnakumar Balasubramanian and Murat A Erdogdu

2023

Gradient-based feature learning under structured data

Alireza Mousavi-Hosseini and Denny Wu and Taiji Suzuki and Murat A Erdogdu

2024

Optimal Excess Risk Bounds for Empirical Risk Minimization on -Norm Linear Regression

Ayoub El Hanchi and Murat A Erdogdu

2024