English

First- and Second-Order Stochastic Adaptive Regularization with Cubics: High Probability Iteration and Sample Complexity

Optimization and Control 2025-04-23 v2

Abstract

We present high-probability (and expectation) complexity bounds for two versions of stochastic adaptive regularization methods with cubics (SARC), also known as regularized Newton methods. The first algorithm aims to find first-order stationary points, while the second targets second-order optimality conditions. Both methods employ stochastic zeroth-, first-, and second-order oracles with specific accuracy and reliability requirements. These oracles, which have been previously used with other stochastic adaptive methods like trust-region and line-search algorithms, are applicable to various optimization settings including expected risk minimization and simulation optimization. In this paper, we establish the first high-probability iteration and sample complexity bounds for both first- and second-order SARC algorithms. Our analysis demonstrates that as in the deterministic case, they outperform other stochastic adaptive methods.

Keywords

Cite

@article{arxiv.2308.13161,
  title  = {First- and Second-Order Stochastic Adaptive Regularization with Cubics: High Probability Iteration and Sample Complexity},
  author = {Katya Scheinberg and Miaolan Xie},
  journal= {arXiv preprint arXiv:2308.13161},
  year   = {2025}
}
R2 v1 2026-06-28T12:04:00.075Z