Tighter Analysis of Alternating Stochastic Gradient Method for Stochastic Nested Problems
arXiv:2106.13781
Abstract
Stochastic nested optimization, including stochastic compositional, min-max and bilevel optimization, is gaining popularity in many machine learning applications. While the three problems share the nested structure, existing works often treat them separately, and thus develop problem-specific algorithms and their analyses. Among various exciting developments, simple SGD-type updates (potentially on multiple variables) are still prevalent in solving this class of nested problems, but they are believed to have slower convergence rate compared to that of the non-nested problems. This paper unifies several SGD-type updates for stochastic nested problems into a single SGD approach that we term ALternating Stochastic gradient dEscenT (ALSET) method. By leveraging the hidden smoothness of the problem, this paper presents a tighter analysis of ALSET for stochastic nested problems. Under the new analysis, to achieve an -stationary point of the nested problem, it requires samples. Under certain regularity conditions, applying our results to stochastic compositional, min-max and reinforcement learning problems either improves or matches the best-known sample complexity in the respective cases. Our results explain why simple SGD-type algorithms in stochastic nested problems all work very well in practice without the need for further modifications.
arXiv commentSubmitted for publication
References in corpus (6)
- Finite-sum Composition Optimization via Variance Reduced Gradient Descent
- Optimal Epoch Stochastic Gradient Descent Ascent Methods for Min-Max Optimization
- Single-Timescale Actor-Critic Provably Finds Globally Optimal Policy
- Provably Faster Algorithms for Bilevel Optimization
- Accelerated Algorithms for Smooth Convex-Concave Minimax Problems with Rate on Squared Gradient Norm
- Randomized Stochastic Variance-Reduced Methods for Multi-Task Stochastic Bilevel Optimization