Murat A. Erdogdu
Murat A. Erdogdu
Verified email at - Homepage
Cited by
Cited by
Seismic: A self-exciting point process model for predicting tweet popularity
Q Zhao, MA Erdogdu, HY He, A Rajaraman, J Leskovec
Proceedings of the 21th ACM SIGKDD international conference on knowledge …, 2015
Convergence rates of sub-sampled Newton methods
MA Erdogdu, A Montanari
Advances in Neural Information Processing Systems, 1090-1098, 2015
Global non-convex optimization with discretized diffusions
MA Erdogdu, L Mackey, O Shamir
arXiv preprint arXiv:1810.12361, 2018
Convergence rates of active learning for maximum likelihood estimation
K Chaudhuri, SM Kakade, P Netrapalli, S Sanghavi
Advances in Neural Information Processing Systems, 1090-1098, 2015
Estimating lasso risk and noise level.
M Bayati, MA Erdogdu, A Montanari
NIPS 26, 944-952, 2013
Stochastic runge-kutta accelerates langevin monte carlo and beyond
X Li, D Wu, L Mackey, MA Erdogdu
arXiv preprint arXiv:1906.07868, 2019
Generalization of two-layer neural networks: An asymptotic viewpoint
J Ba, M Erdogdu, T Suzuki, D Wu, T Zhang
International conference on learning representations, 2019
Flexible results for quadratic forms with applications to variance components estimation
LH Dicker, MA Erdogdu
The Annals of Statistics 45 (1), 386-414, 2017
Maximum likelihood for variance estimation in high-dimensional linear models
LH Dicker, MA Erdogdu
Artificial Intelligence and Statistics, 159-167, 2016
Accelerating SVRG via second-order information
R Kolte, MA Erdogdu, A Ozgür
Neural Information Processing Systems Workshop on Optimization for Machine …, 2015
Convergence rate of block-coordinate maximization Burer–Monteiro method for solving large SDPs
MA Erdogdu, A Ozdaglar, PA Parrilo, ND Vanli
Mathematical Programming, 1-39, 2021
Privacy-utility trade-off for time-series with application to smart-meter data
MA Erdogdu, N Fawaz, A Montanari
Workshops at the Twenty-Ninth AAAI Conference on Artificial Intelligence, 2015
Scaled least squares estimator for glms in large-scale problems
MA Erdogdu, LH Dicker, M Bayati
Advances in Neural Information Processing Systems 29, 3324-3332, 2016
Hausdorff dimension, heavy tails, and generalization in neural networks
U Şimşekli, O Sener, G Deligiannidis, MA Erdogdu
arXiv preprint arXiv:2006.09313, 2020
On the convergence of langevin monte carlo: The interplay between tail growth and smoothness
MA Erdogdu, R Hosseinzadeh
arXiv preprint arXiv:2005.13097, 2020
Normal approximation for stochastic gradient descent via non-asymptotic rates of martingale CLT
A Anastasiou, K Balasubramanian, MA Erdogdu
Conference on Learning Theory, 115-137, 2019
Inference in graphical models via semidefinite programming hierarchies
MA Erdogdu, Y Deshpande, A Montanari
arXiv preprint arXiv:1709.06525, 2017
Robust Estimation of Neural Signals in Calcium Imaging.
H Inan, MA Erdogdu, MJ Schnitzer
NIPS, 2901-2910, 2017
Privacy-utility trade-off under continual observation
MA Erdogdu, N Fawaz
2015 IEEE International Symposium on Information Theory (ISIT), 1801-1805, 2015
Newton-Stein method: A second order method for GLMs via Stein's lemma
MA Erdogdu
Advances in Neural Information Processing Systems 28, 1216-1224, 2015
The system can't perform the operation now. Try again later.
Articles 1–20