Showing math.OCShow all
2 papers · 1 filter
math.OC2026
Long-Run Dynamics of AdaGrad-Norm: Trajectory Stability and Asymptotic Stationarity
Ruinan Jin, Xiaoyu Wang
AdaGrad-Norm is widely studied, yet its long-run behavior in smooth nonconvex optimization remains delicate. For the standard current-denominator recursion, the same stochastic gra…
math.OC2024
Stability and convergence analysis of AdaGrad for non-convex optimization via novel stopping time-based techniques
Ruinan Jin, Xiaoyu Wang, Baoxiang Wang
Adaptive gradient optimizers (AdaGrad), which dynamically adjust the learning rate based on iterative gradients, have emerged as powerful tools in deep learning. These adaptive met…