Nesterov Accelerated Shuffling Gradient Method for Convex Optimization

arXiv2202.03525MaRDI QIDQ6390436

Author name not available (Why is that?)

Publication date: 7 February 2022

Abstract: In this paper, we propose Nesterov Accelerated Shuffling Gradient (NASG), a new algorithm for the convex finite-sum minimization problems. Our method integrates the traditional Nesterov's acceleration momentum with different shuffling sampling schemes. We show that our algorithm has an improved rate of $mathcalO(1/T)$ using unified shuffling schemes, where $T$ is the number of epochs. This rate is better than that of any other shuffling gradient methods in convex regime. Our convergence analysis does not require an assumption on bounded domain or a bounded gradient condition. For randomized shuffling schemes, we improve the convergence bound further. When employing some initial condition, we show that our method converges faster near the small neighborhood of the solution. Numerical simulations demonstrate the efficiency of our algorithm.

Has companion code repository: https://github.com/htt-trangtran/nasg

This page was built for publication: Nesterov Accelerated Shuffling Gradient Method for Convex Optimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6390436)