Second-order methods for quartically-regularised cubic polynomials, with applications to high-order tensor methods

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Cartis, Coralia, Zhu, Wenqi
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916567646732288
author Cartis, Coralia
Zhu, Wenqi
author_facet Cartis, Coralia
Zhu, Wenqi
contents There has been growing interest in high-order tensor methods for nonconvex optimization, with adaptive regularization, as they possess better/optimal worst-case evaluation complexity globally and faster convergence asymptotically. These algorithms crucially rely on repeatedly minimizing nonconvex multivariate Taylor-based polynomial sub-problems, at least locally. Finding efficient techniques for the solution of these sub-problems, beyond the second-order case, has been an open question. This paper proposes a second-order method, Quadratic Quartic Regularisation (QQR), for efficiently minimizing nonconvex quartically-regularized cubic polynomials, such as the AR$p$ sub-problem [3] with $p=3$. Inspired by [35], QQR approximates the third-order tensor term by a linear combination of quadratic and quartic terms, yielding (possibly nonconvex) local models that are solvable to global optimality. In order to achieve accuracy $ε$ in the first-order criticality of the sub-problem in finitely many iterations, we show that the error in the QQR method decreases either linearly or by at least $\mathcal{O}(ε^{4/3})$ for locally convex iterations, while in the nonconvex case, by at least $\mathcal{O}(ε)$; thus improving, on these types of iterations, the general cubic-regularization bound. Preliminary numerical experiments indicate that two QQR variants perform competitively with state-of-the-art approaches such as ARC (also known as AR$p$ with $p=2$), achieving either a lower objective value or iteration counts.
format Preprint
id arxiv_https___arxiv_org_abs_2308_15336
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Second-order methods for quartically-regularised cubic polynomials, with applications to high-order tensor methods
Cartis, Coralia
Zhu, Wenqi
Optimization and Control
Numerical Analysis
There has been growing interest in high-order tensor methods for nonconvex optimization, with adaptive regularization, as they possess better/optimal worst-case evaluation complexity globally and faster convergence asymptotically. These algorithms crucially rely on repeatedly minimizing nonconvex multivariate Taylor-based polynomial sub-problems, at least locally. Finding efficient techniques for the solution of these sub-problems, beyond the second-order case, has been an open question. This paper proposes a second-order method, Quadratic Quartic Regularisation (QQR), for efficiently minimizing nonconvex quartically-regularized cubic polynomials, such as the AR$p$ sub-problem [3] with $p=3$. Inspired by [35], QQR approximates the third-order tensor term by a linear combination of quadratic and quartic terms, yielding (possibly nonconvex) local models that are solvable to global optimality. In order to achieve accuracy $ε$ in the first-order criticality of the sub-problem in finitely many iterations, we show that the error in the QQR method decreases either linearly or by at least $\mathcal{O}(ε^{4/3})$ for locally convex iterations, while in the nonconvex case, by at least $\mathcal{O}(ε)$; thus improving, on these types of iterations, the general cubic-regularization bound. Preliminary numerical experiments indicate that two QQR variants perform competitively with state-of-the-art approaches such as ARC (also known as AR$p$ with $p=2$), achieving either a lower objective value or iteration counts.
title Second-order methods for quartically-regularised cubic polynomials, with applications to high-order tensor methods
topic Optimization and Control
Numerical Analysis
url https://arxiv.org/abs/2308.15336