Mert Gürbüzbalaban

According to our database, Mert Gürbüzbalaban authored at least 62 papers between 2010 and 2024.

Collaborative distances:

• Dijkstra number of three.
• Erdős number of four.

2024

Robust Accelerated Primal-Dual Methods for Computing Saddle Points.

Xuan Zhang, Necdet Serhat Aybat, Mert Gürbüzbalaban

SIAM J. Optim., March, 2024

Differential Privacy of Noisy (S)GD under Heavy-Tailed Perturbations.

Umut Simsekli, Mert Gürbüzbalaban, Sinan Yildirim, Lingjiong Zhu

CoRR, 2024

2023

Boundary Conditions for Linear Exit Time Gradient Trajectories Around Saddle Points: Analysis and Algorithm.

Rishabh Dixit, Mert Gürbüzbalaban, Waheed U. Bajwa

IEEE Trans. Inf. Theory, April, 2023

Cyclic and Randomized Stepsizes Invoke Heavier Tails in SGD than Constant Stepsize.

Mert Gürbüzbalaban, Yuanhan Hu, Umut Simsekli, Lingjiong Zhu

Trans. Mach. Learn. Res., 2023

Accelerated gradient methods for nonconvex optimization: Escape trajectories from strict saddle points and convergence to local minima.

Rishabh Dixit, Mert Gürbüzbalaban, Waheed U. Bajwa

CoRR, 2023

Cyclic and Randomized Stepsizes Invoke Heavier Tails in SGD.

Mert Gürbüzbalaban, Yuanhan Hu, Umut Simsekli, Lingjiong Zhu

CoRR, 2023

Uniform-in-Time Wasserstein Stability Bounds for (Noisy) Stochastic Gradient Descent.

Lingjiong Zhu, Mert Gürbüzbalaban, Anant Raj, Umut Simsekli

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Algorithmic Stability of Heavy-Tailed SGD with General Loss Functions.

Anant Raj, Lingjiong Zhu, Mert Gürbüzbalaban, Umut Simsekli

Proceedings of the International Conference on Machine Learning, 2023

Algorithmic Stability of Heavy-Tailed Stochastic Gradient Descent on Least Squares.

Anant Raj, Melih Barsbey, Mert Gürbüzbalaban, Lingjiong Zhu, Umut Simsekli

Proceedings of the International Conference on Algorithmic Learning Theory, 2023

2022

Randomized Gossiping With Effective Resistance Weights: Performance Guarantees and Applications.

Bugra Can, Saeed Soori, Necdet Serhat Aybat, Maryam Mehri Dehnavi, Mert Gürbüzbalaban

IEEE Trans. Control. Netw. Syst., 2022

Differentially Private Accelerated Optimization Algorithms.

Nurdan Kuru, S. Ilker Birbil, Mert Gürbüzbalaban, Sinan Yildirim

SIAM J. Optim., 2022

A Stochastic Subgradient Method for Distributionally Robust Non-convex and Non-smooth Learning.

Mert Gürbüzbalaban, Andrzej Ruszczynski, Landi Zhu

J. Optim. Theory Appl., 2022

Robust Distributed Accelerated Stochastic Gradient Methods for Multi-Agent Networks.

Alireza Fallah, Mert Gürbüzbalaban, Asuman E. Ozdaglar, Umut Simsekli, Lingjiong Zhu

J. Mach. Learn. Res., 2022

Global Convergence of Stochastic Gradient Hamiltonian Monte Carlo for Nonconvex Stochastic Optimization: Nonasymptotic Performance Bounds and Momentum-Based Acceleration.

Xuefeng Gao, Mert Gürbüzbalaban, Lingjiong Zhu

Oper. Res., 2022

Penalized Langevin and Hamiltonian Monte Carlo Algorithms for Constrained Sampling.

Mert Gürbüzbalaban, Yuanhan Hu, Lingjiong Zhu

CoRR, 2022

Heavy-Tail Phenomenon in Decentralized SGD.

Mert Gürbüzbalaban, Yuanhan Hu, Umut Simsekli, Kun Yuan, Lingjiong Zhu

CoRR, 2022

A Variance-Reduced Stochastic Accelerated Primal Dual Algorithm.

Bugra Can, Mert Gürbüzbalaban, Necdet Serhat Aybat

CoRR, 2022

HyLo: A Hybrid Low-Rank Natural Gradient Descent Method.

Baorun Mu, Saeed Soori, Bugra Can, Mert Gürbüzbalaban, Maryam Mehri Dehnavi

Proceedings of the SC22: International Conference for High Performance Computing, 2022

SAPD+: An Accelerated Stochastic Method for Nonconvex-Concave Minimax Problems.

Xuan Zhang, Necdet Serhat Aybat, Mert Gürbüzbalaban

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

2021

Why random reshuffling beats stochastic gradient descent.

Mert Gürbüzbalaban, Asuman E. Ozdaglar, Pablo A. Parrilo

Math. Program., 2021

Decentralized Stochastic Gradient Langevin Dynamics and Hamiltonian Monte Carlo.

Mert Gürbüzbalaban, Xuefeng Gao, Yuanhan Hu, Lingjiong Zhu

J. Mach. Learn. Res., 2021

TENGraD: Time-Efficient Natural Gradient Descent with Exact Fisher-Block Inversion.

Saeed Soori, Bugra Can, Baourun Mu, Mert Gürbüzbalaban, Maryam Mehri Dehnavi

CoRR, 2021

Convergence Rates of Stochastic Gradient Descent under Infinite Noise Variance.

Hongjian Wang, Mert Gürbüzbalaban, Lingjiong Zhu, Umut Simsekli, Murat A. Erdogdu

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Fractal Structure and Generalization Properties of Stochastic Optimization Algorithms.

Alexander Camuto, George Deligiannidis, Murat A. Erdogdu, Mert Gürbüzbalaban, Umut Simsekli, Lingjiong Zhu

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

The Heavy-Tail Phenomenon in SGD.

Mert Gürbüzbalaban, Umut Simsekli, Lingjiong Zhu

Proceedings of the 38th International Conference on Machine Learning, 2021

Asymmetric Heavy Tails and Implicit Bias in Gaussian Noise Injections.

Alexander Camuto, Xiaoyu Wang, Lingjiong Zhu, Chris C. Holmes, Mert Gürbüzbalaban, Umut Simsekli

Proceedings of the 38th International Conference on Machine Learning, 2021

L-DQN: An Asynchronous Limited-Memory Distributed Quasi-Newton Method.

Bugra Can, Saeed Soori, Maryam Mehri Dehnavi, Mert Gürbüzbalaban

Proceedings of the 2021 60th IEEE Conference on Decision and Control (CDC), 2021

Fractional moment-preserving initialization schemes for training deep neural networks.

Mert Gürbüzbalaban, Yuanhan Hu

Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

2020

Robust Accelerated Gradient Methods for Smooth Strongly Convex Functions.

Necdet Serhat Aybat, Alireza Fallah, Mert Gürbüzbalaban, Asuman E. Ozdaglar

SIAM J. Optim., 2020

Randomness and permutations in coordinate descent methods.

Mert Gürbüzbalaban, Asuman E. Ozdaglar, Nuri Denizcan Vanli, Stephen J. Wright

Math. Program., 2020

A Stochastic Subgradient Method for Distributionally Robust Non-Convex Learning.

Mert Gürbüzbalaban, Andrzej Ruszczynski, Landi Zhu

CoRR, 2020

Fractional moment-preserving initialization schemes for training fully-connected neural networks.

Mert Gürbüzbalaban, Yuanhan Hu

CoRR, 2020

Breaking Reversibility Accelerates Langevin Dynamics for Non-Convex Optimization.

Xuefeng Gao, Mert Gürbüzbalaban, Lingjiong Zhu

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

IDEAL: Inexact DEcentralized Accelerated Augmented Lagrangian Method.

Yossi Arjevani, Joan Bruna, Bugra Can, Mert Gürbüzbalaban, Stefanie Jegelka, Hongzhou Lin

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

ASYNC: A Cloud Engine with Asynchrony and History for Distributed Machine Learning.

Saeed Soori, Bugra Can, Mert Gürbüzbalaban, Maryam Mehri Dehnavi

Proceedings of the 2020 IEEE International Parallel and Distributed Processing Symposium (IPDPS), 2020

Fractional Underdamped Langevin Dynamics: Retargeting SGD with Momentum under Heavy-Tailed Gradient Noise.

Umut Simsekli, Lingjiong Zhu, Yee Whye Teh, Mert Gürbüzbalaban

Proceedings of the 37th International Conference on Machine Learning, 2020

DAve-QN: A Distributed Averaged Quasi-Newton Method with Local Superlinear Convergence Rate.

Saeed Soori, Konstantin Mishchenko, Aryan Mokhtari, Maryam Mehri Dehnavi, Mert Gürbüzbalaban

Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

2019

Convergence Rate of Incremental Gradient and Incremental Newton Methods.

Mert Gürbüzbalaban, Asuman E. Ozdaglar, Pablo A. Parrilo

SIAM J. Optim., 2019

On the Heavy-Tailed Theory of Stochastic Gradient Descent for Deep Neural Networks.

Umut Simsekli, Mert Gürbüzbalaban, Thanh Huy Nguyen, Gaël Richard, Levent Sagun

CoRR, 2019

ASYNC: Asynchronous Machine Learning on Distributed Systems.

Saeed Soori, Bugra Can, Mert Gürbüzbalaban, Maryam Mehri Dehnavi

CoRR, 2019

First Exit Time Analysis of Stochastic Gradient Descent Under Heavy-Tailed Gradient Noise.

Thanh Huy Nguyen, Umut Simsekli, Mert Gürbüzbalaban, Gaël Richard

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

A Universally Optimal Multistage Accelerated Stochastic Gradient Method.

Necdet Serhat Aybat, Alireza Fallah, Mert Gürbüzbalaban, Asuman E. Ozdaglar

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural Networks.

Umut Simsekli, Levent Sagun, Mert Gürbüzbalaban

Proceedings of the 36th International Conference on Machine Learning, 2019

Accelerated Linear Convergence of Stochastic Momentum Methods in Wasserstein Distances.

Bugra Can, Mert Gürbüzbalaban, Lingjiong Zhu

Proceedings of the 36th International Conference on Machine Learning, 2019

2018

Global Convergence Rate of Proximal Incremental Aggregated Gradient Methods.

N. Denizcan Vanli, Mert Gürbüzbalaban, Asuman E. Ozdaglar

SIAM J. Optim., 2018

Surpassing Gradient Descent Provably: A Cyclic Incremental Method with Linear Convergence Rate.

Aryan Mokhtari, Mert Gürbüzbalaban, Alejandro Ribeiro

SIAM J. Optim., 2018

Breaking Reversibility Accelerates Langevin Dynamics for Global Non-Convex Optimization.

Xuefeng Gao, Mert Gürbüzbalaban, Lingjiong Zhu

CoRR, 2018

Global Convergence of Stochastic Gradient Hamiltonian Monte Carlo for Non-Convex Stochastic Optimization: Non-Asymptotic Performance Bounds and Momentum-Based Acceleration.

Xuefeng Gao, Mert Gürbüzbalaban, Lingjiong Zhu

CoRR, 2018

Reducing Communication in Proximal Newton Methods for Sparse Least Squares Problems.

Saeed Soori, Aditya Devarakonda, Zachary Blanco, James Demmel, Mert Gürbüzbalaban, Maryam Mehri Dehnavi

Proceedings of the 47th International Conference on Parallel Processing, 2018

2017

Approximating the Real Structured Stability Radius with Frobenius-Norm Bounded Perturbations.

Nicola Guglielmi, Mert Gürbüzbalaban, Tim Mitchell, Michael L. Overton

SIAM J. Matrix Anal. Appl., 2017

On the Convergence Rate of Incremental Aggregated Gradient Algorithms.

Mert Gürbüzbalaban, Asuman E. Ozdaglar, Pablo A. Parrilo

SIAM J. Optim., 2017

Polynomial root radius optimization with affine constraints.

Julia Eaton, Sara Grundel, Mert Gürbüzbalaban, Michael L. Overton

Math. Program., 2017

Avoiding Communication in Proximal Methods for Convex Optimization Problems.

Saeed Soori, Aditya Devarakonda, James Demmel, Mert Gürbüzbalaban, Maryam Mehri Dehnavi

CoRR, 2017

When Cyclic Coordinate Descent Outperforms Randomized Coordinate Descent.

Mert Gürbüzbalaban, Asuman E. Ozdaglar, Pablo A. Parrilo, Nuri Denizcan Vanli

Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

A double incremental aggregated gradient method with linear convergence rate for large-scale optimization.

Aryan Mokhtari, Mert Gürbüzbalaban, Alejandro Ribeiro

Proceedings of the 2017 IEEE International Conference on Acoustics, 2017

Decentralized computation of effective resistances and acceleration of consensus algorithms.

Necdet Serhat Aybat, Mert Gürbüzbalaban

Proceedings of the 2017 IEEE Global Conference on Signal and Information Processing, 2017

2016

Global convergence rate of incremental aggregated gradient methods for nonsmooth problems.

N. Denizcan Vanli, Mert Gürbüzbalaban, Asuman E. Ozdaglar

Proceedings of the 55th IEEE Conference on Decision and Control, 2016

2015

A globally convergent incremental Newton method.

Mert Gürbüzbalaban, Asuman E. Ozdaglar, Pablo A. Parrilo

Math. Program., 2015

2013

Fast Approximation of the H_INFINITY Norm via Optimization over Spectral Value Sets.

Nicola Guglielmi, Mert Gürbüzbalaban, Michael L. Overton

SIAM J. Matrix Anal. Appl., 2013

2012

Explicit Solutions for Root Optimization of a Polynomial Family With One Affine Constraint.

Vincent D. Blondel, Mert Gürbüzbalaban, Alexandre Megretski, Michael L. Overton

IEEE Trans. Autom. Control., 2012

Some Regularity Results for the Pseudospectral Abscissa and Pseudospectral Radius of a Matrix.

Mert Gürbüzbalaban, Michael L. Overton

SIAM J. Optim., 2012

2010

Explicit solutions for root optimization of a polynomial family.

Vincent D. Blondel, Mert Gürbüzbalaban, Alexandre Megretski, Michael L. Overton

Proceedings of the 49th IEEE Conference on Decision and Control, 2010