3 papers
math.OC2025
Accelerated Gradient Methods with Biased Gradient Estimates: Risk Sensitivity, High-Probability Guarantees, and Large Deviation Bounds
Mert Gürbüzbalaban, Yasa Syed, Necdet Serhat Aybat
We study trade-offs between convergence rate and robustness to gradient errors in the context of first-order methods. Our focus is on generalized momentum methods (GMMs)--a broad c…
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…
stat.CO2023
Optimal randomized multilevel Monte Carlo for repeatedly nested expectations
Yasa Syed, Guanyang Wang
The estimation of repeatedly nested expectations is a challenging task that arises in many real-world systems. However, existing methods generally suffer from high computational co…