Input-Output Stability of Gradient Descent: A Discrete-Time Passivity-Based Approach

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Moalemi, Sepehr, Forbes, James Richard
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909403500773376
author Moalemi, Sepehr
Forbes, James Richard
author_facet Moalemi, Sepehr
Forbes, James Richard
contents This paper presents a discrete-time passivity-based analysis of the gradient descent method for a class of functions with sector-bounded gradients. Using a loop transformation, it is shown that the gradient descent method can be interpreted as a passive controller in negative feedback with a very strictly passive system. The passivity theorem is then used to guarantee input-output stability, as well as the global convergence, of the gradient descent method. Furthermore, provided that the lower and upper sector bounds are not equal, the input-output stability of the gradient descent method is guaranteed using the weak passivity theorem for a larger choice of step size. Finally, to demonstrate the utility of this passivity-based analysis, a new variation of the gradient descent method with variable step size is proposed by gain-scheduling the input and output of the gradient.
format Preprint
id arxiv_https___arxiv_org_abs_2411_16074
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Input-Output Stability of Gradient Descent: A Discrete-Time Passivity-Based Approach
Moalemi, Sepehr
Forbes, James Richard
Optimization and Control
Systems and Control
This paper presents a discrete-time passivity-based analysis of the gradient descent method for a class of functions with sector-bounded gradients. Using a loop transformation, it is shown that the gradient descent method can be interpreted as a passive controller in negative feedback with a very strictly passive system. The passivity theorem is then used to guarantee input-output stability, as well as the global convergence, of the gradient descent method. Furthermore, provided that the lower and upper sector bounds are not equal, the input-output stability of the gradient descent method is guaranteed using the weak passivity theorem for a larger choice of step size. Finally, to demonstrate the utility of this passivity-based analysis, a new variation of the gradient descent method with variable step size is proposed by gain-scheduling the input and output of the gradient.
title Input-Output Stability of Gradient Descent: A Discrete-Time Passivity-Based Approach
topic Optimization and Control
Systems and Control
url https://arxiv.org/abs/2411.16074