The Symmetry Coefficient of Positively Homogeneous Functions

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Nilsson, Max, Giselsson, Pontus
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910918937411584
author Nilsson, Max
Giselsson, Pontus
author_facet Nilsson, Max
Giselsson, Pontus
contents The Bregman distance is a central tool in convex optimization, particularly in first-order gradient descent and proximal-based algorithms. Such methods enable optimization of functions without Lipschitz continuous gradients by leveraging the concept of relative smoothness, with respect to a reference function $h$. A key factor in determining the full range of allowed step sizes in Bregman schemes is the symmetry coefficient, $α(h)$, of the reference function $h$. While some explicit values of $α(h)$ have been determined for specific functions $h$, a general characterization has remained elusive. This paper explores two problems: ($\textit{i}$) deriving calculus rules for the symmetry coefficient and ($\textit{ii}$) computing $α(\lVert\cdot\rVert_2^p)$ for general $p$. We establish upper and lower bounds for the symmetry coefficient of sums of positively homogeneous Legendre functions and, under certain conditions, provide exact formulas for these sums. Furthermore, we demonstrate that $α(\lVert\cdot\rVert_2^p)$ is independent of dimension and propose an efficient algorithm for its computation. Additionally, we prove that $α(\lVert\cdot\rVert_2^p)$ asymptotically equals, and is lower bounded by, the function $1/(2p)$, offering a simpler upper bound for step sizes in Bregman schemes. Finally, we present closed-form computations for specific cases such as $p \in \{6,8,10\}$.
format Preprint
id arxiv_https___arxiv_org_abs_2504_18296
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle The Symmetry Coefficient of Positively Homogeneous Functions
Nilsson, Max
Giselsson, Pontus
Optimization and Control
The Bregman distance is a central tool in convex optimization, particularly in first-order gradient descent and proximal-based algorithms. Such methods enable optimization of functions without Lipschitz continuous gradients by leveraging the concept of relative smoothness, with respect to a reference function $h$. A key factor in determining the full range of allowed step sizes in Bregman schemes is the symmetry coefficient, $α(h)$, of the reference function $h$. While some explicit values of $α(h)$ have been determined for specific functions $h$, a general characterization has remained elusive. This paper explores two problems: ($\textit{i}$) deriving calculus rules for the symmetry coefficient and ($\textit{ii}$) computing $α(\lVert\cdot\rVert_2^p)$ for general $p$. We establish upper and lower bounds for the symmetry coefficient of sums of positively homogeneous Legendre functions and, under certain conditions, provide exact formulas for these sums. Furthermore, we demonstrate that $α(\lVert\cdot\rVert_2^p)$ is independent of dimension and propose an efficient algorithm for its computation. Additionally, we prove that $α(\lVert\cdot\rVert_2^p)$ asymptotically equals, and is lower bounded by, the function $1/(2p)$, offering a simpler upper bound for step sizes in Bregman schemes. Finally, we present closed-form computations for specific cases such as $p \in \{6,8,10\}$.
title The Symmetry Coefficient of Positively Homogeneous Functions
topic Optimization and Control
url https://arxiv.org/abs/2504.18296