Complexity of Inexact Proximal Point Algorithm for minimizing convex functions with Holderian Growth
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2021
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914814361600000 |
|---|---|
| author | Pătraşcu, Andrei Irofti, Paul |
| author_facet | Pătraşcu, Andrei Irofti, Paul |
| contents | Several decades ago the Proximal Point Algorithm (PPA) started to gain a long-lasting attraction for both abstract operator theory and numerical optimization communities. Even in modern applications, researchers still use proximal minimization theory to design scalable algorithms that overcome nonsmoothness. Remarkable works as \cite{Fer:91,Ber:82constrained,Ber:89parallel,Tom:11} established tight relations between the convergence behaviour of PPA and the regularity of the objective function. In this manuscript we derive nonasymptotic iteration complexity of exact and inexact PPA to minimize convex functions under $γ-$Holderian growth: $\BigO{\log(1/ε)}$ (for $γ\in [1,2]$) and $\BigO{1/ε^{γ- 2}}$ (for $γ> 2$). In particular, we recover well-known results on PPA: finite convergence for sharp minima and linear convergence for quadratic growth, even under presence of deterministic noise. Moreover, when a simple Proximal Subgradient Method is recurrently called as an inner routine for computing each IPPA iterate, novel computational complexity bounds are obtained for Restarting Inexact PPA. Our numerical tests show improvements over existing restarting versions of the Subgradient Method. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2108_04482 |
| institution | arXiv |
| publishDate | 2021 |
| record_format | arxiv |
| spellingShingle | Complexity of Inexact Proximal Point Algorithm for minimizing convex functions with Holderian Growth Pătraşcu, Andrei Irofti, Paul Machine Learning Several decades ago the Proximal Point Algorithm (PPA) started to gain a long-lasting attraction for both abstract operator theory and numerical optimization communities. Even in modern applications, researchers still use proximal minimization theory to design scalable algorithms that overcome nonsmoothness. Remarkable works as \cite{Fer:91,Ber:82constrained,Ber:89parallel,Tom:11} established tight relations between the convergence behaviour of PPA and the regularity of the objective function. In this manuscript we derive nonasymptotic iteration complexity of exact and inexact PPA to minimize convex functions under $γ-$Holderian growth: $\BigO{\log(1/ε)}$ (for $γ\in [1,2]$) and $\BigO{1/ε^{γ- 2}}$ (for $γ> 2$). In particular, we recover well-known results on PPA: finite convergence for sharp minima and linear convergence for quadratic growth, even under presence of deterministic noise. Moreover, when a simple Proximal Subgradient Method is recurrently called as an inner routine for computing each IPPA iterate, novel computational complexity bounds are obtained for Restarting Inexact PPA. Our numerical tests show improvements over existing restarting versions of the Subgradient Method. |
| title | Complexity of Inexact Proximal Point Algorithm for minimizing convex functions with Holderian Growth |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2108.04482 |