Mert Gürbüzbalaban

Computer Science · Physical Sciences

16h-index839citations107works0.42yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Stochastic Gradient Optimization Techniques(68), Sparse and Compressive Sensing Techniques(45), Markov Chains and Monte Carlo Methods(22), Advanced Optimization Algorithms Research(19), Statistical Methods and Inference(12)

Publications107 total

Accelerated gradient methods with biased gradient estimates: Risk sensitivity, high-probability guarantees, and large deviation bounds
Journal of Nonlinear and Variational Analysis·2026Open Access
Robustly Stable Accelerated Momentum Methods with a Near-Optimal L2 Gain and H∞ Performance
Mathematics of Operations Research·2025
DIGing--SGLD: Decentralized and Scalable Langevin Sampling over Time--Varying Networks
arXiv (Cornell University)·2025Open Access
Entropic risk-averse generalized momentum methods
Optimization methods & software·2025
Accelerated Gradient Methods with Biased Gradient Estimates: Risk Sensitivity, High-Probability Guarantees, and Large Deviation Bounds
arXiv (Cornell University)·2025Open Access
Mean–semideviation–based distributionally robust learning with weakly convex losses: convergence rates and finite-sample guarantees
Mathematical Programming·2025· 1 citedOpen Access
RESIST: Resilient Decentralized Learning Using Consensus Gradient Descent
arXiv (Cornell University)·2025Open Access
Algorithmic Stability of Stochastic Gradient Descent with Momentum under Heavy-Tailed Noise
arXiv (Cornell University)·2025Open Access
Generalized EXTRA stochastic gradient Langevin dynamics
arXiv (Cornell University)·2024Open Access
Heavy-Tail Phenomenon in Decentralized SGD
IISE Transactions·2024· 4 cited
High-probability complexity guarantees for nonconvex minimax problems
arXiv (Cornell University)·2024Open Access
Robust Accelerated Primal-Dual Methods for Computing Saddle Points
SIAM Journal on Optimization·2024
A Stochastic GDA Method With Backtracking For Solving Nonconvex (Strongly) Concave Minimax Problems
arXiv (Cornell University)·2024· 1 citedOpen Access
Privacy of SGD under Gaussian or Heavy-Tailed Noise: Guarantees without Gradient Clipping
arXiv (Cornell University)·2024Open Access
High-probability complexity bounds for stochastic non-convex minimax optimization
2024
Robustly Stable Accelerated Momentum Methods With A Near-Optimal L2 Gain and $H_\infty$ Performance
arXiv (Cornell University)·2023Open Access
Accelerated Gradient Methods for Nonconvex Optimization: Escape Trajectories From Strict Saddle Points and Convergence to Local Minima
arXiv (Cornell University)·2023Open Access
Uniform-in-Time Wasserstein Stability Bounds for (Noisy) Stochastic Gradient Descent
arXiv (Cornell University)·2023Open Access
High Probability and Risk-Averse Guarantees for a Stochastic Accelerated Primal-Dual Method
arXiv (Cornell University)·2023Open Access
Cyclic and Randomized Stepsizes Invoke Heavier Tails in SGD than Constant Stepsize
arXiv (Cornell University)·2023Open Access
page 1 of 6Next →

Frequent Co-authors

Lingjiong Zhu(15), Umut Şimşekli(13), Asuman Ozdaglar(7), Michael L. Overton(7), Xuefeng Gao(7), Saeed Soori(5), Maryam Mehri Dehnavi(5), Necdet Serhat Aybat(4), Bugra Can(4), Yuanhan Hu(4), N. Denizcan Vanli(4), Aryan Mokhtari(4), Pablo A. Parrilo(3), Levent Sagun(3), Alireza Fallah(3), Thanh Huy Nguyen(3), Gaël Richard(3), Vincent D. Blondel(3), Nicola Guglielmi(2), Alexandre Megretski(2)