Hybrid Stochastic Gradient Descent Algorithms for Stochastic Nonconvex Optimization
(1905.05920)Abstract
We introduce a hybrid stochastic estimator to design stochastic gradient algorithms for solving stochastic optimization problems. Such a hybrid estimator is a convex combination of two existing biased and unbiased estimators and leads to some useful property on its variance. We limit our consideration to a hybrid SARAH-SGD for nonconvex expectation problems. However, our idea can be extended to handle a broader class of estimators in both convex and nonconvex settings. We propose a new single-loop stochastic gradient descent algorithm that can achieve $O(\max{\sigma3\varepsilon{-1},\sigma\varepsilon{-3}})$-complexity bound to obtain an $\varepsilon$-stationary point under smoothness and $\sigma2$-bounded variance assumptions. This complexity is better than $O(\sigma2\varepsilon{-4})$ often obtained in state-of-the-art SGDs when $\sigma < O(\varepsilon{-3})$. We also consider different extensions of our method, including constant and adaptive step-size with single-loop, double-loop, and mini-batch variants. We compare our algorithms with existing methods on several datasets using two nonconvex models.
We're not able to analyze this paper right now due to high demand.
Please check back later (sorry!).
Generate a summary of this paper on our Pro plan:
We ran into a problem analyzing this paper.