English

Subspace Quasi-Newton Method with Gradient Approximation

Optimization and Control 2024-06-05 v1

Abstract

In recent years, various subspace algorithms have been developed to handle large-scale optimization problems. Although existing subspace Newton methods require fewer iterations to converge in practice, the matrix operations and full gradient computation are bottlenecks when dealing with large-scale problems. %In this study, We propose a subspace quasi-Newton method that is restricted to a deterministic-subspace together with a gradient approximation based on random matrix theory. Our method does not require full gradients, let alone Hessian matrices. Yet, it achieves the same order of the worst-case iteration complexities in average for convex and nonconvex cases, compared to existing subspace methods. In numerical experiments, we confirm the superiority of our algorithm in terms of computation time.

Keywords

Cite

@article{arxiv.2406.01965,
  title  = {Subspace Quasi-Newton Method with Gradient Approximation},
  author = {Taisei Miyaishi and Ryota Nozawa and Pierre-Louis Poirion and Akiko Takeda},
  journal= {arXiv preprint arXiv:2406.01965},
  year   = {2024}
}
R2 v1 2026-06-28T16:52:22.491Z