Inexactly Smooth Performance Estimation and New Optimized Gradient Methods

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Zoll, Aaron, Grimmer, Benjamin
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911738994098176
author Zoll, Aaron
Grimmer, Benjamin
author_facet Zoll, Aaron
Grimmer, Benjamin
contents We consider a general class of ``inexactly smooth'' convex functions, providing a universal model capturing as special cases $L$-smooth, $M$-Lipschitz, and Hölder smooth functions, and any combination thereof. Such functions possess a calculus closely following that of smooth functions. Our main results provide inexactly smooth functions with interpolation theorems that are necessary and sufficient up to modest universal constants. These enable analysis of first-order methods for any inexactly smooth convex problem class via solving convex Performance Estimation Problems (PEPs). Further, these enable the extension of Drori and Taylor's constructive approach to algorithm design. From this, we derive an exactly minimax optimal method for $(β,0)$-Hölder smooth problems, methods with the best-known convergence guarantees up to constants for any $(β,p)$-Hölder smooth convex minimization, and a new universal fast backtracking method for any inexactly smooth convex problem.
format Preprint
id arxiv_https___arxiv_org_abs_2606_01505
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Inexactly Smooth Performance Estimation and New Optimized Gradient Methods
Zoll, Aaron
Grimmer, Benjamin
Optimization and Control
We consider a general class of ``inexactly smooth'' convex functions, providing a universal model capturing as special cases $L$-smooth, $M$-Lipschitz, and Hölder smooth functions, and any combination thereof. Such functions possess a calculus closely following that of smooth functions. Our main results provide inexactly smooth functions with interpolation theorems that are necessary and sufficient up to modest universal constants. These enable analysis of first-order methods for any inexactly smooth convex problem class via solving convex Performance Estimation Problems (PEPs). Further, these enable the extension of Drori and Taylor's constructive approach to algorithm design. From this, we derive an exactly minimax optimal method for $(β,0)$-Hölder smooth problems, methods with the best-known convergence guarantees up to constants for any $(β,p)$-Hölder smooth convex minimization, and a new universal fast backtracking method for any inexactly smooth convex problem.
title Inexactly Smooth Performance Estimation and New Optimized Gradient Methods
topic Optimization and Control
url https://arxiv.org/abs/2606.01505