Mert Gürbüzbalaban
Rutgers, The State University of New Jersey
H-index: 23
North America-United States
Top articles of Mert Gürbüzbalaban
Title | Journal | Author(s) | Publication Date |
---|---|---|---|
Robust accelerated primal-dual methods for computing saddle points | accepted to SIAM Journal on Optimization (arXiv preprint arXiv:2111.12743) | Xuan Zhang Necdet Serhat Aybat Mert Gürbüzbalaban | 2021/11/24 |
A Stochastic GDA Method With Backtracking For Solving Nonconvex (Strongly) Concave Minimax Problems | arXiv preprint arXiv:2403.07806 | Qiushui Xu Xuan Zhang Necdet Serhat Aybat Mert Gürbüzbalaban | 2024/3/12 |
Uniform-in-Time Wasserstein Stability Bounds for (Noisy) Stochastic Gradient Descent | Advances in Neural Information Processing Systems | Lingjiong Zhu Mert Gurbuzbalaban Anant Raj Umut Simsekli | 2024/2/13 |
Algorithmic stability of heavy-tailed stochastic gradient descent on least squares | Anant Raj Melih Barsbey Mert Gurbuzbalaban Lingjiong Zhu Umut Şim | 2023/2/13 | |
Robustly Stable Accelerated Momentum Methods With A Near-Optimal L2 Gain and Performance | arXiv preprint arXiv:2309.11481 | Mert Gurbuzbalaban | 2023/9/20 |
Cyclic and Randomized Stepsizes Invoke Heavier Tails in SGD than Constant Stepsize | arXiv preprint arXiv:2302.05516 | Mert Gürbüzbalaban Yuanhan Hu Umut Şimşekli Lingjiong Zhu | 2023/2/10 |
Accelerated gradient methods for nonconvex optimization: Escape trajectories from strict saddle points and convergence to local minima | arXiv preprint arXiv:2307.07030 | Rishabh Dixit Mert Gurbuzbalaban Waheed U Bajwa | 2023/7/13 |
Distributionally robust learning with weakly convex losses: Convergence rates and finite-sample guarantees | arXiv preprint arXiv:2301.06619 | Landi Zhu Mert Gürbüzbalaban Andrzej Ruszczyński | 2023/1/16 |
Algorithmic stability of heavy-tailed sgd with general loss functions | Anant Raj Lingjiong Zhu Mert Gurbuzbalaban Umut Simsekli | 2023/7/3 | |
Exit time analysis for approximations of gradient descent trajectories around saddle points | Information and Inference: A Journal of the IMA | Rishabh Dixit Mert Gürbüzbalaban Waheed U Bajwa | 2023/6 |
High probability and risk-averse guarantees for stochastic saddle point problems | arXiv preprint arXiv:2304.00444 | Yassine Laguel Necdet Serhat Aybat Mert Gürbüzbalaban | 2023/4/2 |
Randomized gossiping with effective resistance weights: Performance guarantees and applications | IEEE Transactions on Control of Network Systems | Maryam Mehri Dehnavi Bugra Can Mert Gurbuzbalaban Necdet Serhat Aybat Saeed Soori | 2022 |
HyLo: a hybrid low-rank natural gradient descent method | Baorun Mu Saeed Soori Bugra Can Mert Gürbüzbalaban Maryam Mehri Dehnavi | 2022/11/13 | |
A Variance-Reduced Stochastic Accelerated Primal Dual Algorithm | arXiv preprint arXiv:2202.09688 | Bugra Can Mert Gurbuzbalaban Necdet Serhat Aybat | 2022/2/19 |
Boundary Conditions for Linear Exit Time Gradient Trajectories Around Saddle Points: Analysis and Algorithm | IEEE Transactions on Information Theory | Rishabh Dixit Mert Gürbüzbalaban Waheed U Bajwa | 2022/10/10 |
Differentially private accelerated optimization algorithms | SIAM Journal on Optimization | Nurdan Kuru Ş İlker Birbil Mert Gurbuzbalaban Sinan Yildirim | 2022 |
A stochastic subgradient method for distributionally robust non-convex and non-smooth learning | Journal of Optimization Theory and Applications | Mert Gürbüzbalaban Andrzej Ruszczyński Landi Zhu | 2022/9 |
Robust distributed accelerated stochastic gradient methods for multi-agent networks | Journal of machine learning research | Alireza Fallah Mert Gürbüzbalaban Asuman Ozdaglar Umut Şimşekli Lingjiong Zhu | 2022 |
Heavy-tail phenomenon in decentralized sgd | arXiv preprint arXiv:2205.06689 | Mert Gurbuzbalaban Yuanhan Hu Umut Simsekli Kun Yuan Lingjiong Zhu | 2022/5/13 |
Sapd+: An accelerated stochastic method for nonconvex-concave minimax problems | Advances in Neural Information Processing Systems | Xuan Zhang Necdet Serhat Aybat Mert Gurbuzbalaban | 2022/5/30 |