activity
20162025
most citedDAve-QN: A Distributed Averaged Quasi-Newton Method with Local Superlinear Convergence Rate

14 citations · 51 across the 12 of their papers we have counts for

collaborators

14 papers

math.OC2025

An Accelerated Primal Dual Algorithm with Backtracking for Decentralized Constrained Optimization

Qiushui Xu, Necdet Serhat Aybat, Mert Gürbüzbalaban

We propose a distributed accelerated primal-dual method with backtracking (D-APDB) for cooperative multi-agent constrained consensus optimization problems over an undirected networ…

math.OC2024

High-probability complexity guarantees for nonconvex minimax problems

Yassine Laguel, Yasa Syed, Necdet Serhat Aybat +1

Stochastic smooth nonconvex minimax problems are prevalent in machine learning, e.g., GAN training, fair classification, and distributionally robust learning. Stochastic gradient d…

math.OC2024★ 1 cited

A Stochastic GDA Method With Backtracking For Solving Nonconvex Concave Minimax Problems

Necdet Serhat Aybat, Qiushui Xu, Xuan Zhang +1

We propose a stochastic GDA (gradient descent ascent) method with backtracking (SGDA-B) to solve nonconvex-concave (NCC) minimax problems of the form: $\min_{\mathbf{x}} \max_y \su…

stat.ML2024

Privacy of SGD under Gaussian or Heavy-Tailed Noise: Guarantees without Gradient Clipping

Umut Şimşekli, Mert Gürbüzbalaban, Sinan Yıldırım +1

The injection of heavy-tailed noise into the iterates of stochastic gradient descent (SGD) has garnered growing interest in recent years due to its theoretical and empirical benefi…

math.OC2023★ 2 cited

Distributionally Robust Learning with Weakly Convex Losses: Convergence Rates and Finite-Sample Guarantees

Landi Zhu, Mert Gürbüzbalaban, Andrzej Ruszczyński

We consider a distributionally robust stochastic optimization problem and formulate it as a stochastic two-level composition optimization problem with the use of the mean--semidevi…

stat.ML2022★ 1 cited

Heavy-Tail Phenomenon in Decentralized SGD

Mert Gurbuzbalaban, Yuanhan Hu, Umut Simsekli +2

Recent theoretical studies have shown that heavy-tails can emerge in stochastic optimization due to `multiplicative noise', even under surprisingly simple settings, such as linear…