Mert Gürbüzbalaban

Publication Activity (10 Years)

Years Active: 2010-2024
Publications (10 Years): 75

Top Topics

Convergence Rate

Stochastic Gradient

Top Venues

Publications

Umut Simsekli, Mert Gürbüzbalaban, Sinan Yildirim, Lingjiong Zhu
Differential Privacy of Noisy (S)GD under Heavy-Tailed Perturbations. CoRR (2024)
Xuan Zhang, Necdet Serhat Aybat, Mert Gürbüzbalaban
Robust Accelerated Primal-Dual Methods for Computing Saddle Points. SIAM J. Optim. 34 (1) (2024)
Lingjiong Zhu, Mert Gürbüzbalaban, Anant Raj, Umut Simsekli
Uniform-in-Time Wasserstein Stability Bounds for (Noisy) Stochastic Gradient Descent. NeurIPS (2023)
Mert Gürbüzbalaban, Yuanhan Hu, Umut Simsekli, Lingjiong Zhu
Cyclic and Randomized Stepsizes Invoke Heavier Tails in SGD. CoRR (2023)
Mert Gürbüzbalaban, Yuanhan Hu, Umut Simsekli, Lingjiong Zhu
Cyclic and Randomized Stepsizes Invoke Heavier Tails in SGD than Constant Stepsize. Trans. Mach. Learn. Res. 2023 (2023)
Lingjiong Zhu, Mert Gürbüzbalaban, Anant Raj, Umut Simsekli
Uniform-in-Time Wasserstein Stability Bounds for (Noisy) Stochastic Gradient Descent. CoRR (2023)
Rishabh Dixit, Mert Gürbüzbalaban, Waheed U. Bajwa
Accelerated gradient methods for nonconvex optimization: Escape trajectories from strict saddle points and convergence to local minima. CoRR (2023)
Anant Raj, Lingjiong Zhu, Mert Gürbüzbalaban, Umut Simsekli
Algorithmic Stability of Heavy-Tailed SGD with General Loss Functions. CoRR (2023)
Anant Raj, Melih Barsbey, Mert Gürbüzbalaban, Lingjiong Zhu, Umut Simsekli
Algorithmic Stability of Heavy-Tailed Stochastic Gradient Descent on Least Squares. ALT (2023)
Anant Raj, Lingjiong Zhu, Mert Gürbüzbalaban, Umut Simsekli
Algorithmic Stability of Heavy-Tailed SGD with General Loss Functions. ICML (2023)
Rishabh Dixit, Mert Gürbüzbalaban, Waheed U. Bajwa
Boundary Conditions for Linear Exit Time Gradient Trajectories Around Saddle Points: Analysis and Algorithm. IEEE Trans. Inf. Theory 69 (4) (2023)
Xuan Zhang, Necdet Serhat Aybat, Mert Gürbüzbalaban
SAPD+: An Accelerated Stochastic Method for Nonconvex-Concave Minimax Problems. NeurIPS (2022)
Xuefeng Gao, Mert Gürbüzbalaban, Lingjiong Zhu
Global Convergence of Stochastic Gradient Hamiltonian Monte Carlo for Nonconvex Stochastic Optimization: Nonasymptotic Performance Bounds and Momentum-Based Acceleration. Oper. Res. 70 (5) (2022)
Mert Gürbüzbalaban, Andrzej Ruszczynski, Landi Zhu
A Stochastic Subgradient Method for Distributionally Robust Non-convex and Non-smooth Learning. J. Optim. Theory Appl. 194 (3) (2022)
Bugra Can, Saeed Soori, Necdet Serhat Aybat, Maryam Mehri Dehnavi, Mert Gürbüzbalaban
Randomized Gossiping With Effective Resistance Weights: Performance Guarantees and Applications. IEEE Trans. Control. Netw. Syst. 9 (2) (2022)
Nurdan Kuru, S. Ilker Birbil, Mert Gürbüzbalaban, Sinan Yildirim
Differentially Private Accelerated Optimization Algorithms. SIAM J. Optim. 32 (2) (2022)
Anant Raj, Melih Barsbey, Mert Gürbüzbalaban, Lingjiong Zhu, Umut Simsekli
Algorithmic Stability of Heavy-Tailed Stochastic Gradient Descent on Least Squares. CoRR (2022)
Mert Gürbüzbalaban, Yuanhan Hu, Umut Simsekli, Kun Yuan, Lingjiong Zhu
Heavy-Tail Phenomenon in Decentralized SGD. CoRR (2022)
Mert Gürbüzbalaban, Yuanhan Hu, Lingjiong Zhu
Penalized Langevin and Hamiltonian Monte Carlo Algorithms for Constrained Sampling. CoRR (2022)
Baorun Mu, Saeed Soori, Bugra Can, Mert Gürbüzbalaban, Maryam Mehri Dehnavi
HyLo: A Hybrid Low-Rank Natural Gradient Descent Method. SC (2022)
Bugra Can, Mert Gürbüzbalaban, Necdet Serhat Aybat
A Variance-Reduced Stochastic Accelerated Primal Dual Algorithm. CoRR (2022)
Alireza Fallah, Mert Gürbüzbalaban, Asuman E. Ozdaglar, Umut Simsekli, Lingjiong Zhu
Robust Distributed Accelerated Stochastic Gradient Methods for Multi-Agent Networks. J. Mach. Learn. Res. 23 (2022)
Bugra Can, Saeed Soori, Maryam Mehri Dehnavi, Mert Gürbüzbalaban
L-DQN: An Asynchronous Limited-Memory Distributed Quasi-Newton Method. CDC (2021)
Alexander Camuto, George Deligiannidis, Murat A. Erdogdu, Mert Gürbüzbalaban, Umut Simsekli, Lingjiong Zhu
Fractal Structure and Generalization Properties of Stochastic Optimization Algorithms. NeurIPS (2021)
Mert Gürbüzbalaban, Asuman E. Ozdaglar, Pablo A. Parrilo
Why random reshuffling beats stochastic gradient descent. Math. Program. 186 (1) (2021)
Mert Gürbüzbalaban, Xuefeng Gao, Yuanhan Hu, Lingjiong Zhu
Decentralized Stochastic Gradient Langevin Dynamics and Hamiltonian Monte Carlo. J. Mach. Learn. Res. 22 (2021)
Alexander Camuto, Xiaoyu Wang, Lingjiong Zhu, Chris C. Holmes, Mert Gürbüzbalaban, Umut Simsekli
Asymmetric Heavy Tails and Implicit Bias in Gaussian Noise Injections. CoRR (2021)
Saeed Soori, Bugra Can, Baourun Mu, Mert Gürbüzbalaban, Maryam Mehri Dehnavi
TENGraD: Time-Efficient Natural Gradient Descent with Exact Fisher-Block Inversion. CoRR (2021)
Bugra Can, Saeed Soori, Maryam Mehri Dehnavi, Mert Gürbüzbalaban
L-DQN: An Asynchronous Limited-Memory Distributed Quasi-Newton Method. CoRR (2021)
Mert Gürbüzbalaban, Yuanhan Hu
Fractional moment-preserving initialization schemes for training deep neural networks. AISTATS (2021)
Alexander Camuto, George Deligiannidis, Murat A. Erdogdu, Mert Gürbüzbalaban, Umut Simsekli, Lingjiong Zhu
Fractal Structure and Generalization Properties of Stochastic Optimization Algorithms. CoRR (2021)
Alexander Camuto, Xiaoyu Wang, Lingjiong Zhu, Chris C. Holmes, Mert Gürbüzbalaban, Umut Simsekli
Asymmetric Heavy Tails and Implicit Bias in Gaussian Noise Injections. ICML (2021)
Hongjian Wang, Mert Gürbüzbalaban, Lingjiong Zhu, Umut Simsekli, Murat A. Erdogdu
Convergence Rates of Stochastic Gradient Descent under Infinite Noise Variance. NeurIPS (2021)
Mert Gürbüzbalaban, Umut Simsekli, Lingjiong Zhu
The Heavy-Tail Phenomenon in SGD. ICML (2021)
Mert Gürbüzbalaban, Andrzej Ruszczynski, Landi Zhu
A Stochastic Subgradient Method for Distributionally Robust Non-Convex Learning. CoRR (2020)
Saeed Soori, Konstantin Mishchenko, Aryan Mokhtari, Maryam Mehri Dehnavi, Mert Gürbüzbalaban
DAve-QN: A Distributed Averaged Quasi-Newton Method with Local Superlinear Convergence Rate. AISTATS (2020)
Nurdan Kuru, S. Ilker Birbil, Mert Gürbüzbalaban, Sinan Yildirim
Differentially Private Accelerated Optimization Algorithms. CoRR (2020)
Yossi Arjevani, Joan Bruna, Bugra Can, Mert Gürbüzbalaban, Stefanie Jegelka, Hongzhou Lin
IDEAL: Inexact DEcentralized Accelerated Augmented Lagrangian Method. CoRR (2020)
Necdet Serhat Aybat, Alireza Fallah, Mert Gürbüzbalaban, Asuman E. Ozdaglar
Robust Accelerated Gradient Methods for Smooth Strongly Convex Functions. SIAM J. Optim. 30 (1) (2020)
Saeed Soori, Bugra Can, Mert Gürbüzbalaban, Maryam Mehri Dehnavi
ASYNC: A Cloud Engine with Asynchrony and History for Distributed Machine Learning. IPDPS (2020)
Mert Gürbüzbalaban, Yuanhan Hu
Fractional moment-preserving initialization schemes for training fully-connected neural networks. CoRR (2020)
Xuefeng Gao, Mert Gürbüzbalaban, Lingjiong Zhu
Breaking Reversibility Accelerates Langevin Dynamics for Non-Convex Optimization. NeurIPS (2020)
Mert Gürbüzbalaban, Xuefeng Gao, Yuanhan Hu, Lingjiong Zhu
Decentralized Stochastic Gradient Langevin Dynamics and Hamiltonian Monte Carlo. CoRR (2020)
Yossi Arjevani, Joan Bruna, Bugra Can, Mert Gürbüzbalaban, Stefanie Jegelka, Hongzhou Lin
IDEAL: Inexact DEcentralized Accelerated Augmented Lagrangian Method. NeurIPS (2020)
Mert Gürbüzbalaban, Asuman E. Ozdaglar, Nuri Denizcan Vanli, Stephen J. Wright
Randomness and permutations in coordinate descent methods. Math. Program. 181 (2) (2020)
Mert Gürbüzbalaban, Umut Simsekli, Lingjiong Zhu
The Heavy-Tail Phenomenon in SGD. CoRR (2020)
Umut Simsekli, Lingjiong Zhu, Yee Whye Teh, Mert Gürbüzbalaban
Fractional Underdamped Langevin Dynamics: Retargeting SGD with Momentum under Heavy-Tailed Gradient Noise. CoRR (2020)
Umut Simsekli, Lingjiong Zhu, Yee Whye Teh, Mert Gürbüzbalaban
Fractional Underdamped Langevin Dynamics: Retargeting SGD with Momentum under Heavy-Tailed Gradient Noise. ICML (2020)
Necdet Serhat Aybat, Alireza Fallah, Mert Gürbüzbalaban, Asuman E. Ozdaglar
A Universally Optimal Multistage Accelerated Stochastic Gradient Method. CoRR (2019)
Alireza Fallah, Mert Gürbüzbalaban, Asuman E. Ozdaglar, Umut Simsekli, Lingjiong Zhu
Robust Distributed Accelerated Stochastic Gradient Methods for Multi-Agent Networks. CoRR (2019)
Bugra Can, Mert Gürbüzbalaban, Lingjiong Zhu
Accelerated Linear Convergence of Stochastic Momentum Methods in Wasserstein Distances. CoRR (2019)
Bugra Can, Mert Gürbüzbalaban, Lingjiong Zhu
Accelerated Linear Convergence of Stochastic Momentum Methods in Wasserstein Distances. ICML (2019)
Umut Simsekli, Levent Sagun, Mert Gürbüzbalaban
A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural Networks. CoRR (2019)
Umut Simsekli, Mert Gürbüzbalaban, Thanh Huy Nguyen, Gaël Richard, Levent Sagun
On the Heavy-Tailed Theory of Stochastic Gradient Descent for Deep Neural Networks. CoRR (2019)
Necdet Serhat Aybat, Alireza Fallah, Mert Gürbüzbalaban, Asuman E. Ozdaglar
A Universally Optimal Multistage Accelerated Stochastic Gradient Method. NeurIPS (2019)
Thanh Huy Nguyen, Umut Simsekli, Mert Gürbüzbalaban, Gaël Richard
First Exit Time Analysis of Stochastic Gradient Descent Under Heavy-Tailed Gradient Noise. CoRR (2019)
Umut Simsekli, Levent Sagun, Mert Gürbüzbalaban
A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural Networks. ICML (2019)
Mert Gürbüzbalaban, Asuman E. Ozdaglar, Pablo A. Parrilo
Convergence Rate of Incremental Gradient and Incremental Newton Methods. SIAM J. Optim. 29 (4) (2019)
Saeed Soori, Bugra Can, Mert Gürbüzbalaban, Maryam Mehri Dehnavi
ASYNC: Asynchronous Machine Learning on Distributed Systems. CoRR (2019)
Thanh Huy Nguyen, Umut Simsekli, Mert Gürbüzbalaban, Gaël Richard
First Exit Time Analysis of Stochastic Gradient Descent Under Heavy-Tailed Gradient Noise. NeurIPS (2019)
Necdet Serhat Aybat, Alireza Fallah, Mert Gürbüzbalaban, Asuman E. Ozdaglar
Robust Accelerated Gradient Methods for Smooth Strongly Convex Functions. CoRR (2018)
Xuefeng Gao, Mert Gürbüzbalaban, Lingjiong Zhu
Global Convergence of Stochastic Gradient Hamiltonian Monte Carlo for Non-Convex Stochastic Optimization: Non-Asymptotic Performance Bounds and Momentum-Based Acceleration. CoRR (2018)
N. Denizcan Vanli, Mert Gürbüzbalaban, Asuman E. Ozdaglar
Global Convergence Rate of Proximal Incremental Aggregated Gradient Methods. SIAM J. Optim. 28 (2) (2018)
Aryan Mokhtari, Mert Gürbüzbalaban, Alejandro Ribeiro
Surpassing Gradient Descent Provably: A Cyclic Incremental Method with Linear Convergence Rate. SIAM J. Optim. 28 (2) (2018)
Saeed Soori, Aditya Devarakonda, Zachary Blanco, James Demmel, Mert Gürbüzbalaban, Maryam Mehri Dehnavi
Reducing Communication in Proximal Newton Methods for Sparse Least Squares Problems. ICPP (2018)
Xuefeng Gao, Mert Gürbüzbalaban, Lingjiong Zhu
Breaking Reversibility Accelerates Langevin Dynamics for Global Non-Convex Optimization. CoRR (2018)
Mert Gürbüzbalaban, Asuman E. Ozdaglar, Pablo A. Parrilo, Nuri Denizcan Vanli
When Cyclic Coordinate Descent Outperforms Randomized Coordinate Descent. NIPS (2017)
Julia Eaton, Sara Grundel, Mert Gürbüzbalaban, Michael L. Overton
Polynomial root radius optimization with affine constraints. Math. Program. 165 (2) (2017)
Nicola Guglielmi, Mert Gürbüzbalaban, Tim Mitchell, Michael L. Overton
Approximating the Real Structured Stability Radius with Frobenius-Norm Bounded Perturbations. SIAM J. Matrix Anal. Appl. 38 (4) (2017)
Aryan Mokhtari, Mert Gürbüzbalaban, Alejandro Ribeiro
A double incremental aggregated gradient method with linear convergence rate for large-scale optimization. ICASSP (2017)
Necdet Serhat Aybat, Mert Gürbüzbalaban
Decentralized computation of effective resistances and acceleration of consensus algorithms. GlobalSIP (2017)
Mert Gürbüzbalaban, Asuman E. Ozdaglar, Pablo A. Parrilo
On the Convergence Rate of Incremental Aggregated Gradient Algorithms. SIAM J. Optim. 27 (2) (2017)
Saeed Soori, Aditya Devarakonda, James Demmel, Mert Gürbüzbalaban, Maryam Mehri Dehnavi
Avoiding Communication in Proximal Methods for Convex Optimization Problems. CoRR (2017)
N. Denizcan Vanli, Mert Gürbüzbalaban, Asuman E. Ozdaglar
Global convergence rate of incremental aggregated gradient methods for nonsmooth problems. CDC (2016)
Aryan Mokhtari, Mert Gürbüzbalaban, Alejandro Ribeiro
Surpassing Gradient Descent Provably: A Cyclic Incremental Method with Linear Convergence Rate. CoRR (2016)
Mert Gürbüzbalaban, Asuman E. Ozdaglar, Pablo A. Parrilo
A globally convergent incremental Newton method. Math. Program. 151 (1) (2015)
Nicola Guglielmi, Mert Gürbüzbalaban, Michael L. Overton
Norm via Optimization over Spectral Value Sets. SIAM J. Matrix Anal. Appl. 34 (2) (2013)
Mert Gürbüzbalaban, Michael L. Overton
Some Regularity Results for the Pseudospectral Abscissa and Pseudospectral Radius of a Matrix. SIAM J. Optim. 22 (2) (2012)
Vincent D. Blondel, Mert Gürbüzbalaban, Alexandre Megretski, Michael L. Overton
Explicit Solutions for Root Optimization of a Polynomial Family With One Affine Constraint. IEEE Trans. Autom. Control. 57 (12) (2012)
Vincent D. Blondel, Mert Gürbüzbalaban, Alexandre Megretski, Michael L. Overton
Explicit solutions for root optimization of a polynomial family. CDC (2010)