Skip to content

Home Search Authors Pakistan News Saved

SciRah

SciRah does not host or store research papers. Results come live from free, official scholarly APIs, and every paper links back to its original source.

Data sources

OpenAlex
Semantic Scholar
Crossref
CORE
arXiv
PubMed

Privacy policy Terms of service

M. Gürbüzbalaban · SciRah

Researcher profile · Semantic Scholar

M. Gürbüzbalaban

Share profile

M. Gürbüzbalaban — researcher profile on SciRah

h-index: 24
Works: 65
Citations: 2,167

Most-cited papers

A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural Networks
Umut Simsekli, Levent Sagun, M. Gürbüzbalaban
2019International Conference on Machine Learning375 citations
Semantic Scholar
The Heavy-Tail Phenomenon in SGD
M. Gürbüzbalaban, Umut Simsekli, Lingjiong Zhu
2020International Conference on Machine Learning193 citations
Semantic Scholar
Why random reshuffling beats stochastic gradient descent
M. Gürbüzbalaban, A. Ozdaglar, P. Parrilo
2015Mathematical programming191 citations Open access
Semantic Scholar
On the Convergence Rate of Incremental Aggregated Gradient Algorithms
M. Gürbüzbalaban, A. Ozdaglar, P. Parrilo
2015SIAM Journal on Optimization153 citations Open access
Semantic Scholar
First Exit Time Analysis of Stochastic Gradient Descent Under Heavy-Tailed Gradient Noise
T. Nguyen, Umut Simsekli, M. Gürbüzbalaban, G. Richard
2019Neural Information Processing Systems84 citations
Semantic Scholar
Global Convergence of Stochastic Gradient Hamiltonian Monte Carlo for Non-Convex Stochastic Optimization: Non-Asymptotic Performance Bounds and Momentum-Based Acceleration
Xue-Feng Gao, M. Gürbüzbalaban, Lingjiong Zhu
2018Operational Research74 citations Open access
Semantic Scholar
On the Heavy-Tailed Theory of Stochastic Gradient Descent for Deep Neural Networks
Umut Simsekli, M. Gürbüzbalaban, T. Nguyen, G. Richard +1 more
2019arXiv.org73 citations
Semantic Scholar
A Universally Optimal Multistage Accelerated Stochastic Gradient Method
N. Aybat, Alireza Fallah, M. Gürbüzbalaban, A. Ozdaglar
2019Neural Information Processing Systems66 citations
Semantic Scholar
Robust Accelerated Gradient Methods for Smooth Strongly Convex Functions
N. Aybat, Alireza Fallah, M. Gürbüzbalaban, A. Ozdaglar
2018SIAM Journal on Optimization66 citations Open access
Semantic Scholar
Fractional Underdamped Langevin Dynamics: Retargeting SGD with Momentum under Heavy-Tailed Gradient Noise
Umut Simsekli, Lingjiong Zhu, Y. Teh, M. Gürbüzbalaban
2020International Conference on Machine Learning63 citations
Semantic Scholar
SAPD+: An Accelerated Stochastic Method for Nonconvex-Concave Minimax Problems
Xuan Zhang, N. Aybat, M. Gürbüzbalaban
2022Neural Information Processing Systems55 citations Open access
Semantic Scholar
Convergence Rate of Incremental Gradient and Incremental Newton Methods
M. Gürbüzbalaban, A. Ozdaglar, P. Parrilo
2015SIAM Journal on Optimization51 citations Open access
Semantic Scholar
Accelerated Linear Convergence of Stochastic Momentum Methods in Wasserstein Distances
Bugra Can, M. Gürbüzbalaban, Lingjiong Zhu
2019International Conference on Machine Learning50 citations
Semantic Scholar
A globally convergent incremental Newton method
M. Gürbüzbalaban, A. Ozdaglar, P. Parrilo
2014Mathematical programming50 citations Open access
Semantic Scholar
FAST APPROXIMATION OF THE H∞ NORM VIA OPTIMIZATION OVER SPECTRAL VALUE SETS∗
N. Guglielmi, M. Gürbüzbalaban, M. Overton
201245 citations
Semantic Scholar
Surpassing Gradient Descent Provably: A Cyclic Incremental Method with Linear Convergence Rate
Aryan Mokhtari, M. Gürbüzbalaban, Alejandro Ribeiro
2016SIAM Journal on Optimization42 citations Open access
Semantic Scholar
Fast Approximation of the HINFINITY Norm via Optimization over Spectral Value Sets
N. Guglielmi, M. Gürbüzbalaban, M. Overton
2013SIAM Journal on Matrix Analysis and Applications42 citations
Semantic Scholar
When Cyclic Coordinate Descent Outperforms Randomized Coordinate Descent
M. Gürbüzbalaban, A. Ozdaglar, P. Parrilo, N. D. Vanli
2017Neural Information Processing Systems39 citations
Semantic Scholar
Breaking Reversibility Accelerates Langevin Dynamics for Global Non-Convex Optimization
Xue-Feng Gao, M. Gürbüzbalaban, Lingjiong Zhu
2018Neural Information Processing Systems38 citations
Semantic Scholar
On Nesterov's Nonsmooth Chebyshev-Rosenbrock Functions
M. Gürbüzbalaban, M. Overton
201236 citations Open access
Semantic Scholar
Decentralized Stochastic Gradient Langevin Dynamics and Hamiltonian Monte Carlo
M. Gürbüzbalaban, Xue-Feng Gao, Yuanhan Hu, Lingjiong Zhu
2020Journal of machine learning research32 citations
Semantic Scholar
Robust Accelerated Primal-Dual Methods for Computing Saddle Points
Xuan Zhang, N. Aybat, M. Gürbüzbalaban
2021SIAM Journal on Optimization31 citations Open access
Semantic Scholar
Differentially Private Accelerated Optimization Algorithms
Nurdan Kuru, Ş. Birbil, M. Gürbüzbalaban, S. Yıldırım
2020SIAM Journal on Optimization29 citations Open access
Semantic Scholar
Algorithmic Stability of Heavy-Tailed SGD with General Loss Functions
Anant Raj, Lingjiong Zhu, M. Gürbüzbalaban, Umut Simsekli
2023International Conference on Machine Learning27 citations Open access
Semantic Scholar
IDEAL: Inexact DEcentralized Accelerated Augmented Lagrangian Method
Yossi Arjevani, Joan Bruna, Bugra Can, M. Gürbüzbalaban +2 more
2020Neural Information Processing Systems23 citations
Semantic Scholar
Penalized Overdamped and Underdamped Langevin Monte Carlo Algorithms for Constrained Sampling
M. Gürbüzbalaban, Yuanhan Hu, Lingjiong Zhu
2022Journal of machine learning research22 citations
Semantic Scholar
A Stochastic Subgradient Method for Distributionally Robust Non-convex and Non-smooth Learning
M. Gürbüzbalaban, A. Ruszczynski, Landi Zhu
2022Journal of Optimization Theory and Applications19 citations
Semantic Scholar
Decentralized computation of effective resistances and acceleration of consensus algorithms
N. Aybat, M. Gürbüzbalaban
2017IEEE Global Conference on Signal and Information Processing19 citations Open access
Semantic Scholar
Asymmetric Heavy Tails and Implicit Bias in Gaussian Noise Injections
A. Camuto, Xiao-Yu Wang, Lingjiong Zhu, Chris C. Holmes +2 more
2021International Conference on Machine Learning17 citations
Semantic Scholar
Algorithmic Stability of Heavy-Tailed Stochastic Gradient Descent on Least Squares
Anant Raj, Melih Barsbey, M. Gürbüzbalaban, Lingjiong Zhu +1 more
2022International Conference on Algorithmic Learning Theory15 citations Open access
Semantic Scholar
Fractional moment-preserving initialization schemes for training deep neural networks
M. Gürbüzbalaban, Yuanhan Hu
2021International Conference on Artificial Intelligence and Statistics14 citations
Semantic Scholar
TENGraD: Time-Efficient Natural Gradient Descent with Exact Fisher-Block Inversion
Saeed Soori, Bugra Can, Baorun Mu, M. Gürbüzbalaban +1 more
2021arXiv.org12 citations
Semantic Scholar
Uniform-in-Time Wasserstein Stability Bounds for (Noisy) Stochastic Gradient Descent
Lingjiong Zhu, M. Gürbüzbalaban, Anant Raj, Umut Simsekli
2023Neural Information Processing Systems10 citations Open access
Semantic Scholar
Generalized EXTRA stochastic gradient Langevin dynamics
M. Gürbüzbalaban, Mohammad Rafiqul Islam, Xiao-Yu Wang, Lin Zhu
2024arXiv.org9 citations
Semantic Scholar
Breaking Reversibility Accelerates Langevin Dynamics for Non-Convex Optimization
Xue-Feng Gao, M. Gürbüzbalaban, Lingjiong Zhu
2020Neural Information Processing Systems9 citations
Semantic Scholar
A Stochastic Subgradient Method for Distributionally Robust Non-Convex Learning
M. Gürbüzbalaban, A. Ruszczynski, Landi Zhu
2020arXiv.org9 citations
Semantic Scholar
Randomized Gossiping With Effective Resistance Weights: Performance Guarantees and Applications
Bugra Can, Saeed Soori, N. Aybat, Maryam Mehri Dehnavi +1 more
2019IEEE Transactions on Control of Network Systems9 citations Open access
Semantic Scholar
Approximating the Real Structured Stability Radius with Frobenius-Norm Bounded Perturbations
N. Guglielmi, M. Gürbüzbalaban, Tim Mitchell, M. Overton
2017SIAM Journal on Matrix Analysis and Applications9 citations Open access
Semantic Scholar
Some Regularity Results for the Pseudospectral Abscissa and Pseudospectral Radius of a Matrix
M. Gürbüzbalaban, M. Overton
2012SIAM Journal on Optimization9 citations Open access
Semantic Scholar
HyLo: A Hybrid Low-Rank Natural Gradient Descent Method
Baorun Mu, Saeed Soori, Bugra Can, M. Gürbüzbalaban +1 more
2022International Conference for High Performance Computing, Networking, Storage and Analysis8 citations
Semantic Scholar
Avoiding Communication in Proximal Methods for Convex Optimization Problems
Saeed Soori, Aditya Devarakonda, J. Demmel, M. Gürbüzbalaban +1 more
2017arXiv.org7 citations
Semantic Scholar
Accelerated gradient methods for nonconvex optimization: Escape trajectories from strict saddle points and convergence to local minima
Rishabh Dixit, M. Gürbüzbalaban, W. Bajwa
2023Foundations of Computational Mathematics6 citations Open access
Semantic Scholar
Theory and methods for problems arising in robust stability, optimization and quantization
M. Overton, C. Gunturk, M. Gürbüzbalaban
20126 citations
Semantic Scholar
A Variance-Reduced Stochastic Accelerated Primal Dual Algorithm
Bugra Can, M. Gürbüzbalaban, N. Aybat
2022arXiv.org5 citations
Semantic Scholar
A double incremental aggregated gradient method with linear convergence rate for large-scale optimization
Aryan Mokhtari, M. Gürbüzbalaban, Alejandro Ribeiro
2017IEEE International Conference on Acoustics, Speech, and Signal Processing5 citations
Semantic Scholar
DIGing-SGLD: Decentralized and Scalable Langevin Sampling over Time-Varying Networks
W. U. Bajwa, M. Gürbüzbalaban, Mustafa Ali Kutbay, Ling-Jiong Zhu +1 more
2025arXiv.org3 citations
Semantic Scholar
Cyclic and Randomized Stepsizes Invoke Heavier Tails in SGD
M. Gürbüzbalaban, Yuanhan Hu, Umut Simsekli, Lingjiong Zhu
2023Trans. Mach. Learn. Res.3 citations Open access
Semantic Scholar
Fractional moment-preserving initialization schemes for training fully-connected neural networks
M. Gürbüzbalaban, Yuanhan Hu
2020arXiv.org3 citations
Semantic Scholar
Mean–semideviation–based distributionally robust learning with weakly convex losses: convergence rates and finite-sample guarantees
Landi Zhu, M. Gürbüzbalaban, Andrzej Ruszczynski
2025Mathematical programming2 citations Open access
Semantic Scholar
High-probability complexity bounds for stochastic non-convex minimax optimization
Yassine Laguel, Yasa Syed, N. Aybat, M. Gürbüzbalaban
2024Neural Information Processing Systems2 citations
Semantic Scholar

Frequent co-authors

Invite them to SciRah by sharing their profile.

Lingjiong Zhu×13
Invite
Lingjiong Zhu — researcher profile on SciRah
Umut Simsekli×10
Invite
Umut Simsekli — researcher profile on SciRah
N. Aybat×8
Invite
N. Aybat — researcher profile on SciRah
A. Ozdaglar×7
Invite
A. Ozdaglar — researcher profile on SciRah

×6

Invite

Bugra Can — researcher profile on SciRah

Invite

M. Overton — researcher profile on SciRah

Invite

P. Parrilo — researcher profile on SciRah

Invite

Yuanhan Hu — researcher profile on SciRah

Xue-Feng Gao×4

Invite

Xue-Feng Gao — researcher profile on SciRah

Invite

Saeed Soori — researcher profile on SciRah

Maryam Mehri Dehnavi×4

Invite

Maryam Mehri Dehnavi — researcher profile on SciRah

N. Guglielmi×3

Invite

N. Guglielmi — researcher profile on SciRah