Asymptotic and Non-Asymptotic Convergence of AdaGrad for Non-Convex Optimization via Novel Stopping Time-based Analysis

Adaptive optimizers have emerged as powerful tools in deep learning, dynamically adjusting the learning rate based on iterative gradients. These adaptive methods have significantly succeeded in various deep learning tasks, outperforming stochastic gradient descent (SGD). However, despite AdaGrad's status as a cornerstone of adaptive optimization, its theoretical analysis has not adequately addressed key aspects such as asymptotic convergence and non-asymptotic convergence rates in non-convex optimization scenarios. This study aims to provide a comprehensive analysis of AdaGrad, filling the existing gaps in the literature. We introduce an innovative stopping time technique from probabilistic theory, which allows us to establish the stability of AdaGrad under mild conditions for the first time. We further derive the asymptotically almost sure and mean-square convergence for AdaGrad. In addition, we demonstrate the near-optimal non-asymptotic convergence rate measured by the average-squared gradients in expectation, which is stronger than the existing high-probability results. The techniques developed in this work are potentially independent of interest for future research on other adaptive stochastic algorithms.