Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.02763 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909000497364992 |
|---|---|
| author | Zeng, Ziyang Zhang, Junyu He, Chuan |
| author_facet | Zeng, Ziyang Zhang, Junyu He, Chuan |
| contents | In this paper, we study Newton-conjugate gradient (Newton-CG) methods for minimizing a nonconvex function $f$ whose Hessian is $(H_f,ν)$-Hölder continuous with modulus $H_f>0$ and exponent $ν\in(0,1]$. Recently proposed Newton-CG methods for this problem adopt (i) non-adaptive regularization and (ii) a nested line-search procedure, where (i) often leads to inefficient early progress and the loss of local superlinear convergence, and (ii) may incur high computational cost due to multiple solves of the Newton system per iteration. To address these limitations, we propose two novel Newton-CG algorithms, depending on the availability of $ν$, that adaptively regularize the Newton system by leveraging the auto-conditioning technique to eliminate the nested line search. The proposed algorithms achieve the best-known iteration complexity ${\mathcal O}\big(H_f^{1/(1+ν)}ε^{-(2+ν)/(1+ν)}\big)$ for finding an $ε$-stationary point and, simultaneously, enjoy local superlinear convergence near nondegenerate local minimizers. Numerical experiments further demonstrate the practical advantages of our algorithms over existing approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_02763 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Adaptive Newton-CG methods with global and local analysis for unconstrained optimization with Hölder continuous Hessian Zeng, Ziyang Zhang, Junyu He, Chuan Optimization and Control In this paper, we study Newton-conjugate gradient (Newton-CG) methods for minimizing a nonconvex function $f$ whose Hessian is $(H_f,ν)$-Hölder continuous with modulus $H_f>0$ and exponent $ν\in(0,1]$. Recently proposed Newton-CG methods for this problem adopt (i) non-adaptive regularization and (ii) a nested line-search procedure, where (i) often leads to inefficient early progress and the loss of local superlinear convergence, and (ii) may incur high computational cost due to multiple solves of the Newton system per iteration. To address these limitations, we propose two novel Newton-CG algorithms, depending on the availability of $ν$, that adaptively regularize the Newton system by leveraging the auto-conditioning technique to eliminate the nested line search. The proposed algorithms achieve the best-known iteration complexity ${\mathcal O}\big(H_f^{1/(1+ν)}ε^{-(2+ν)/(1+ν)}\big)$ for finding an $ε$-stationary point and, simultaneously, enjoy local superlinear convergence near nondegenerate local minimizers. Numerical experiments further demonstrate the practical advantages of our algorithms over existing approaches. |
| title | Adaptive Newton-CG methods with global and local analysis for unconstrained optimization with Hölder continuous Hessian |
| topic | Optimization and Control |
| url | https://arxiv.org/abs/2604.02763 |