Characterization of Convex Objective Functions and Optimal Expected Convergence Rates for SGDDownload PDFOpen Website

2019 (modified: 11 Nov 2022)ICML 2019Readers: Everyone
Abstract: We study Stochastic Gradient Descent (SGD) with diminishing step sizes for convex objective functions. We introduce a definitional framework and theory that defines and characterizes a core propert...
0 Replies

Loading