We study variance reduction for non-convex optimization when gradient evaluations return with a delay. The server can update the parameter while earlier evaluations remain unfinished. We first analyze an ordered recursive momentum estimator for stochastic optimization. Under average smoothness and bounded variance, its...
In this paper, we study the last-iterate convergence of clipped stochastic gradient descent under heavy-tailed noise. We assume that the stochastic gradients are unbiased and that the noise has a bounded central $p$-th moment, where $1<p\le2$. For smooth convex objectives, a linearly decreasing learning rate gives a hi...
Variance reduction improves the convergence rate of stochastic non-convex optimization under the average smoothness condition. Existing adaptive variance reduction methods are especially designed for average smoothness and do not adapt to standard smoothness. In this paper, we study how one algorithm can adapt to these...
Stochastic recursive momentum (STORM) achieves fast convergence for nonconvex optimization via the variance reduction effect, but existing analyses rely on the strong average smoothness assumption. In this paper, we study the convergence of STORM for different objectives without average smoothness. We first revisit the...
Wei Jiang, Yi-Bo Wang, Wen-Hao Yang et al.· 0 citations
A momentum-based estimator with mini-batches is employed to track the function values of each level, which are subsequently used to construct momentum gradient estimators, and a batch-free method that incorporates a first-order approximation and a clipping technique for function value estimation is developed.
Wei Jiang, Rui Yan, Si-Fan Yang et al.· 0 citations
This paper solves the problem of sign-based variance reduction methods' failure to obtain optimal convergence rates for both nonconvex stochastic and finite-sum optimization, and proposes tracking the global gradient at the server through unbiased compression of recursive gradient increments.
This paper studies projection-free algorithms for stochastic constrained multi-level compositional optimization and proposes variance-reduced projection-free algorithms and establishes complexity guarantees under both the Frank-Wolfe gap and the gradient mapping criteria.
Wei Jiang, Si-Fan Yang, Wen-Hao Yang et al.· 3 citations
Traditional variance reduction methods (e.g., SPIDER, SARAH, STORM) have been extensively investigated for improving the convergence rates of stochastic optimization. These techniques typically maintain a sequence of estimators for a single function (or gradient) across iterations. However, what if we need to track mul...
Wei Jiang, Si-Fan Yang, Yi-Bo Wang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.