Skip to yearly menu bar Skip to main content


Poster

On the Convergence to a Global Solution of Shuffling-Type Gradient Algorithms

Lam Nguyen · Trang H. Tran

Great Hall & Hall B1+B2 (level 1) #1101

Abstract:

Stochastic gradient descent (SGD) algorithm is the method of choice in many machine learning tasks thanks to its scalability and efficiency in dealing with large-scale problems. In this paper, we focus on the shuffling version of SGD which matches the mainstream practical heuristics. We show the convergence to a global solution of shuffling SGD for a class of non-convex functions under over-parameterized settings. Our analysis employs more relaxed non-convex assumptions than previous literature. Nevertheless, we maintain the desired computational complexity as shuffling SGD has achieved in the general convex setting.

Chat is not available.