Structure, Analysis, and Synthesis of First-Order Algorithms

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Miller, Jared, Scherer, Carsten, Jakob, Fabian, Iannelli, Andrea
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912982812852224
author Miller, Jared
Scherer, Carsten
Jakob, Fabian
Iannelli, Andrea
author_facet Miller, Jared
Scherer, Carsten
Jakob, Fabian
Iannelli, Andrea
contents Optimization algorithms can be interpreted through the lens of dynamical systems as the interconnection of linear systems and a set of subgradient nonlinearities. This dynamical systems formulation allows for the analysis and synthesis of optimization algorithms by solving robust control problems. In this work, we use the celebrated internal model principle in control theory to structurally factorize convergent composite optimization algorithms into suitable network-dependent internal models and core subcontrollers. As the key benefit, we reveal that this permits us to synthesize optimization algorithms even if information is transmitted over networks featuring dynamical phenomena such as time delays, channel memory, or crosstalk. Design of these algorithms is achieved under bisection in the exponential convergence rate either through a nonconvex local search or by alternation of convex semidefinite programs. We demonstrate factorization of existing optimization algorithms and the automated synthesis of new optimization algorithms in the networked setting.
format Preprint
id arxiv_https___arxiv_org_abs_2603_24795
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Structure, Analysis, and Synthesis of First-Order Algorithms
Miller, Jared
Scherer, Carsten
Jakob, Fabian
Iannelli, Andrea
Optimization and Control
Systems and Control
90C25, 90C90, 93D20, 93-08, 93C10, 90C22, 90C46
Optimization algorithms can be interpreted through the lens of dynamical systems as the interconnection of linear systems and a set of subgradient nonlinearities. This dynamical systems formulation allows for the analysis and synthesis of optimization algorithms by solving robust control problems. In this work, we use the celebrated internal model principle in control theory to structurally factorize convergent composite optimization algorithms into suitable network-dependent internal models and core subcontrollers. As the key benefit, we reveal that this permits us to synthesize optimization algorithms even if information is transmitted over networks featuring dynamical phenomena such as time delays, channel memory, or crosstalk. Design of these algorithms is achieved under bisection in the exponential convergence rate either through a nonconvex local search or by alternation of convex semidefinite programs. We demonstrate factorization of existing optimization algorithms and the automated synthesis of new optimization algorithms in the networked setting.
title Structure, Analysis, and Synthesis of First-Order Algorithms
topic Optimization and Control
Systems and Control
90C25, 90C90, 93D20, 93-08, 93C10, 90C22, 90C46
url https://arxiv.org/abs/2603.24795