Line search methods with variable sample size for unconstrained optimization

26 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates (2019, methodology): “Other authors [23, 13, 18, 64, 43] use a line-search termination criteria that requires function/gradient evaluations averaged over multiple samples.”
Subsampled inexact Newton methods for minimizing large sums of convex functions (2018, background): “…small sample subset at the beginning of iterative process and increasing the sample size as the solution is approached, ranging from simple heuristic approach [19, 9] to elaborate schemes that take into account the progress achieved up to the current iteration, [1, 2, 3, 6, 15, 24, 25, 26, 33, 35].”