Imagen de Portada

Exact worst-case convergence rates of gradient descent: a complete analysis for all constant stepsizes over nonconvex and convex functions

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Rotaru, Teodor, Glineur, François, Patrinos, Panagiotis
Formato:	Preprint
Publicado:	2024
Materias:	Optimization and Control
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Improved convergence rates for the Difference-of-Convex algorithm
por: Rotaru, Teodor, et al.
Publicado: (2024)

Tight Analysis of Difference-of-Convex Algorithm (DCA) Improves Convergence Rates for Proximal Gradient Descent
por: Rotaru, Teodor, et al.
Publicado: (2025)

Tight Convergence Rates in Gradient Mapping for the Difference-of-Convex Algorithm
por: Rotaru, Teodor, et al.
Publicado: (2025)

Worst-case convergence analysis of relatively inexact gradient descent on smooth convex functions
por: Vernimmen, Pierre, et al.
Publicado: (2025)

Analytic analysis of the worst-case complexity of the gradient method with exact line search and the Polyak stepsize
por: Huang, Ya-Kui, et al.
Publicado: (2024)

Exact Convergence rate of the subgradient method by using Polyak step size
por: Zamani, Moslem, et al.
Publicado: (2024)

Global and local approaches for the minimization of a sum of pointwise minima of convex functions
por: Van Dessel, Guillaume, et al.
Publicado: (2025)

Exact worst-case convergence rates for Douglas--Rachford and Davis--Yin splitting methods
por: Nguyen, Edward Duc Hien, et al.
Publicado: (2025)

Nonlinear conjugate gradient methods: worst-case convergence rates via computer-assisted analyses
por: Gupta, Shuvomoy Das, et al.
Publicado: (2023)

Second-order methods for provably escaping strict saddle points in composite nonconvex and nonsmooth optimization
por: Bodard, Alexander, et al.
Publicado: (2025)

Empirical and computer-aided robustness analysis of long-step and accelerated methods in smooth convex optimization
por: Vernimmen, Pierre, et al.
Publicado: (2025)

Projected gradient methods for nonconvex and stochastic smooth optimization: new complexities and auto-conditioned stepsizes
por: Lan, Guanghui, et al.
Publicado: (2024)

On the convergence of proximal gradient methods for convex simple bilevel optimization
por: Latafat, Puya, et al.
Publicado: (2023)

Presolve techniques for quasi-convex chance constraints with finite-support low-dimensional uncertainty
por: Van Dessel, Guillaume, et al.
Publicado: (2025)

Forward-backward splitting under the light of generalized convexity
por: Oikonomidis, Konstantinos, et al.
Publicado: (2025)

On the convergence analysis of the decentralized projected gradient descent method
por: Choi, Woocheol, et al.
Publicado: (2023)

The inexact power augmented Lagrangian method for constrained nonconvex optimization
por: Bodard, Alexander, et al.
Publicado: (2024)

Dualities for non-Euclidean smoothness and strong convexity under the light of generalized conjugacy
por: Laude, Emanuel, et al.
Publicado: (2021)

On the convergence result of the gradient-push algorithm on directed graphs with constant stepsize
por: Choi, Woocheol, et al.
Publicado: (2023)

Proximal gradient methods with inexact oracle of degree q for composite optimization
por: Nabou, Yassine, et al.
Publicado: (2024)

Global minimization of a minimum of a finite collection of functions
por: Van Dessel, Guillaume, et al.
Publicado: (2024)

Global minimisation of nonconvex functions by generalising the mirror descent method
por: Millán, Reinier Díaz, et al.
Publicado: (2024)

Block-coordinate and incremental aggregated proximal gradient methods for nonsmooth nonconvex problems
por: Latafat, Puya, et al.
Publicado: (2019)

A unified framework for inexact adaptive stepsizes in the gradient methods, the conjugate gradient methods and the quasi-Newton methods for strictly convex quadratic optimization
por: Liu, Zexian
Publicado: (2026)

PEPit: computer-assisted worst-case analyses of first-order optimization methods in Python
por: Goujaud, Baptiste, et al.
Publicado: (2022)

A consensus-based optimization method for nonsmooth nonconvex programs with approximated gradient descent scheme
por: Wei, Jiazhen, et al.
Publicado: (2025)

On convergence rates of subgradient descent on semialgebraic functions
por: Chzhen, Evgenii, et al.
Publicado: (2026)

Optimal and parameter-free gradient minimization methods for convex and nonconvex optimization
por: Lan, Guanghui, et al.
Publicado: (2023)

Long-time dynamics and universality of nonconvex gradient descent
por: Han, Qiyang
Publicado: (2025)

A Bregman forward-backward linesearch algorithm for nonconvex composite optimization: superlinear convergence to nonisolated local minima
por: Ahookhosh, Masoud, et al.
Publicado: (2019)

Nonlinearly preconditioned gradient flows
por: Oikonomidis, Konstantinos, et al.
Publicado: (2025)

Escaping saddle points without Lipschitz smoothness: the power of nonlinear preconditioning
por: Bodard, Alexander, et al.
Publicado: (2025)

Anisotropic Proximal Point Algorithm
por: Laude, Emanuel, et al.
Publicado: (2023)

Anisotropic Proximal Gradient
por: Laude, Emanuel, et al.
Publicado: (2022)

Newton methods beyond Hessian Lipschitz continuity: A nonlinear preconditioning approach
por: Bodard, Alexander, et al.
Publicado: (2026)

Dual first-order methods for efficient computation of convex hull prices
por: Tanji, Sofiane, et al.
Publicado: (2025)

Proximal gradient-type method with generalized distance and convergence analysis without global descent lemma
por: Yagishita, Shotaro, et al.
Publicado: (2025)

Nonconvex optimization and convergence of stochastic gradient descent, and solution of asynchronous game
por: Buck, Kevin, et al.
Publicado: (2025)

A short proof of near-linear convergence of adaptive gradient descent under fourth-order growth and convexity
por: Davis, Damek, et al.
Publicado: (2026)

Bregman Finito/MISO for nonconvex regularized finite sum minimization without Lipschitz gradient continuity
por: Latafat, Puya, et al.
Publicado: (2021)