Some Worst-Case Datasets of Deterministic First-Order Methods for Solving Binary Logistic Regression

Abstract

We present in this paper some worst-case datasets of deterministic first-order methods for solving large-scale binary logistic regression problems. Under the assumption that the number of algorithm iterations is much smaller than the problem dimension, with our worst-case datasets it requires at least $\mathcal{O}(1/\sqrt{\epsilon })$ first-order oracle inquiries to compute an $\epsilon$-approximate solution. From traditional iteration complexity analysis point of view, the binary logistic regression loss functions with our worst-case datasets are new worst-case function instances among the class of smooth convex optimization problems.