Saved in:
Bibliographic Details
Main Authors: Lara, Felipe, Marcavillaca, Raúl T., Vuong, Phan T.
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.03534
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916423584972800
author Lara, Felipe
Marcavillaca, Raúl T.
Vuong, Phan T.
author_facet Lara, Felipe
Marcavillaca, Raúl T.
Vuong, Phan T.
contents We study differentiable strongly quasiconvex functions for providing new properties for algorithmic and monotonicity purposes. Furthemore, we provide insights into the decreasing behaviour of strongly quasiconvex functions, applying this for establishing exponential convergence for first- and second-order gradient systems without relying on the usual Lipschitz continuity assumption on the gradient of the function. The explicit discretization of the first-order dynamical system leads to the gradient descent method while discretization of the second-order dynamical system with viscous damping recovers the heavy ball method. We establish the linear convergence of both methods under suitable conditions on the parameters as well as comparisons with other classes of nonconvex functions used in the gradient descent literature.
format Preprint
id arxiv_https___arxiv_org_abs_2410_03534
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Characterizations, Dynamical Systems and Gradient Methods for Strongly Quasiconvex Functions
Lara, Felipe
Marcavillaca, Raúl T.
Vuong, Phan T.
Optimization and Control
We study differentiable strongly quasiconvex functions for providing new properties for algorithmic and monotonicity purposes. Furthemore, we provide insights into the decreasing behaviour of strongly quasiconvex functions, applying this for establishing exponential convergence for first- and second-order gradient systems without relying on the usual Lipschitz continuity assumption on the gradient of the function. The explicit discretization of the first-order dynamical system leads to the gradient descent method while discretization of the second-order dynamical system with viscous damping recovers the heavy ball method. We establish the linear convergence of both methods under suitable conditions on the parameters as well as comparisons with other classes of nonconvex functions used in the gradient descent literature.
title Characterizations, Dynamical Systems and Gradient Methods for Strongly Quasiconvex Functions
topic Optimization and Control
url https://arxiv.org/abs/2410.03534