Aggregating regular norms

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Juditsky, Anatoli, Nemirovski, Arkadi
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911774351032320
author Juditsky, Anatoli
Nemirovski, Arkadi
author_facet Juditsky, Anatoli
Nemirovski, Arkadi
contents The subject of this paper is regularity-preserving aggregation of regular norms on finite-dimensional linear spaces. Regular norms were introduced in [5] and are closely related to ``type 2'' spaces [9, Chapter 9] playing important role in 1) high-dimensional convex geometry and probability in Banach spaces [0.9.12.13.15], and in 2) design of proximal first-order algorithms for large-scale convex optimization with dimension-independent, or nearly so, complexity. Regularity, with moderate parameters, of a norm makes applicable, in a dimension-independent fashion, numerous geometric, probabilistic, and optimization-related results, which motivates our interest in aggregating regular norms with controlled (and moderate) inflation of regularity parameters.
format Preprint
id arxiv_https___arxiv_org_abs_2210_16664
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Aggregating regular norms
Juditsky, Anatoli
Nemirovski, Arkadi
Optimization and Control
52A21, 90C06, 90C25
The subject of this paper is regularity-preserving aggregation of regular norms on finite-dimensional linear spaces. Regular norms were introduced in [5] and are closely related to ``type 2'' spaces [9, Chapter 9] playing important role in 1) high-dimensional convex geometry and probability in Banach spaces [0.9.12.13.15], and in 2) design of proximal first-order algorithms for large-scale convex optimization with dimension-independent, or nearly so, complexity. Regularity, with moderate parameters, of a norm makes applicable, in a dimension-independent fashion, numerous geometric, probabilistic, and optimization-related results, which motivates our interest in aggregating regular norms with controlled (and moderate) inflation of regularity parameters.
title Aggregating regular norms
topic Optimization and Control
52A21, 90C06, 90C25
url https://arxiv.org/abs/2210.16664