2017 · 29 citations · 17 references
Natural SciencesComputer ScienceAlgorithmsMachine LearningOptimizationConvex OptimizationNonlinear ProgrammingOptimization For Machine LearningRobust OptimizationStochastic OptimizationStochastic ProgrammingConvergence Rate AnalysisLarge-scale Convex OptimizationLipschitz ConditionsLipschitz ContinuityLipschitz OptimizationStochastic CompositionStochastic Convex OptimizationStochastic Gradient Descent
We consider the stochastic composition optimization problem proposed in \cite{wang2017stochastic}, which has applications ranging from estimation to statistical and machine learning. We propose the first ADMM based algorithm named com SVR ADMM, and show that com SVR ADMM converges linearly for strongly convex and Lipschitz smooth objectives, and has a convergence rate of $O(\logS/S)$, which improves upon the $O(S^{-4/9})$ rate in \cite{wang2016accelerating} when the objective is convex and Lipschitz smooth. Moreover, com SVR ADMM possesses a rate of $O(1/\sqrt{S})$ when the objective is convex but without Lipschitz smoothness. We also conduct experiments and show that it outperforms existing algorithms.
17
Reinforcement Learning: An Introduction
Richard S. Sutton, Andy Barto · IEEE Transactions on Neural Networks · 1998 · 27.1K citations