Mert Gurbuzbalaban

Assistant Professor, Rutgers University

Joined

November 2017

Names

Mert Gurbuzbalaban

MERT GURBUZBALABAN

Mert Gürbüzbalaban

Emails

****@gmail.com (Confirmed)

****@mit.edu (Confirmed)

****@rutgers.edu (Confirmed)

****@business.rutgers.edu (Confirmed)

Personal Links

DBLP

Career & Education History

Assistant Professor

Rutgers University (rutgers.edu)

2016 – Present

Postdoc

Massachusetts Institute of Technology (mit.edu)

2014 – 2016

PhD student

New York University (nyu.edu)

2007 – 2014

Advisors, Relations & Conflicts

PhD Advisor

Michael Overton

2007 – 2012

PhD Advisor

Sinan Gunturk

2007 – 2012

Expertise

Machine Learning

2012 – Present

Optimization

2007 – Present

Publications

High-probability complexity bounds for stochastic non-convex minimax optimization
Yassine Laguel, Yasa Syed, Necdet Aybat, Mert Gurbuzbalaban
- NeurIPS 2024 poster
- Readers: Everyone
Cyclic and Randomized Stepsizes Invoke Heavier Tails in SGD than Constant Stepsize
Mert Gurbuzbalaban, Yuanhan Hu, Umut Simsekli, Lingjiong Zhu
- Accepted by TMLR
- Readers: Everyone
Uniform-in-Time Wasserstein Stability Bounds for (Noisy) Stochastic Gradient Descent
Lingjiong Zhu, Mert Gurbuzbalaban, Anant Raj, Umut Simsekli
- NeurIPS 2023 poster
- Readers: Everyone
Algorithmic Stability of Heavy-Tailed SGD with General Loss Functions
Anant Raj, Lingjiong Zhu, Mert Gurbuzbalaban, Umut Simsekli
- ICML 2023 Poster
- Readers: Everyone
SAPD+: An Accelerated Stochastic Method for Nonconvex-Concave Minimax Problems
Xuan Zhang, Necdet Aybat, Mert Gurbuzbalaban
- Published: 31 Oct 2022, Last Modified: 16 Jan 2023
- NeurIPS 2022 Accept
- Readers: Everyone
Convergence Rates of Stochastic Gradient Descent under Infinite Noise Variance
Hongjian Wang, Mert Gurbuzbalaban, Lingjiong Zhu, Umut Simsekli, Murat A Erdogdu
- Published: 09 Nov 2021, Last Modified: 05 May 2023
- NeurIPS 2021 Poster
- Readers: Everyone
Fractal Structure and Generalization Properties of Stochastic Optimization Algorithms
Alexander Camuto, George Deligiannidis, Murat A Erdogdu, Mert Gurbuzbalaban, Umut Simsekli, Lingjiong Zhu
- Published: 09 Nov 2021, Last Modified: 05 May 2023
- NeurIPS 2021 Spotlight
- Readers: Everyone
Differentially Private Accelerated Optimization Algorithms
Nurdan Kuru, Ilker Birbil, Mert Gurbuzbalaban, Sinan Yıldırım
- 12 May 2021
- OpenReview Archive Direct Upload
- Readers: Everyone
The Heavy-Tail Phenomenon in SGD
Mert Gurbuzbalaban, Umut Simsekli, Lingjiong Zhu
- 28 Sept 2020 (modified: 12 Oct 2025)
- ICLR 2021 Conference Blind Submission
- Readers: Everyone
A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural Networks
Umut Simsekli, Levent Sagun, Mert Gürbüzbalaban
- 2019 (modified: 11 Nov 2022)
- ICML 2019
- Readers: Everyone

View all 12 publications

Mert Gurbuzbalaban

Names

Emails

Personal Links

Career & Education History

Advisors, Relations & Conflicts

Expertise

Publications

Co-Authors