Imagen de Portada

Provable non-accelerations of the heavy-ball method

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Goujaud, Baptiste, Taylor, Adrien, Dieuleveut, Aymeric
Formato:	Preprint
Publicado:	2023
Materias:	Optimization and Control
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Counter-examples in first-order optimization: a constructive approach
por: Goujaud, Baptiste, et al.
Publicado: (2023)

Open Problem: Two Riddles in Heavy-Ball Dynamics
por: Goujaud, Baptiste, et al.
Publicado: (2025)

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

An optimal first-order method for smooth and strongly convex composite optimization and its stationary limit
por: Upadhyaya, Manu, et al.
Publicado: (2026)

Tight analyses of first-order methods with error feedback
por: Thomsen, Daniel Berg, et al.
Publicado: (2025)

A Tight Theory of Error Feedback Algorithms in Distributed Optimization
por: Thomsen, Daniel Berg, et al.
Publicado: (2026)

Compressed and distributed least-squares regression: convergence rates with applications to Federated Learning
por: Philippenko, Constantin, et al.
Publicado: (2023)

Unified Breakdown Analysis for Byzantine Robust Gossip
por: Gaucher, Renaud, et al.
Publicado: (2024)

From Inexact Gradients to Byzantine Robustness: Acceleration and Optimization under Similarity
por: Gaucher, Renaud, et al.
Publicado: (2026)

Scaffold with Stochastic Gradients: New Analysis with Linear Speed-Up
por: Mangold, Paul, et al.
Publicado: (2025)

Gradient Descent Is Optimal Under Lower Restricted Secant Inequality And Upper Error Bound
por: Guille-Escuret, Charles, et al.
Publicado: (2022)

On growth error bound conditions with an application to heavy ball method
por: Jin, Qinian
Publicado: (2023)

Federated Majorize-Minimization: Beyond Parameter Aggregation
por: Dieuleveut, Aymeric, et al.
Publicado: (2025)

Refined Analysis of Federated Averaging and Federated Richardson-Romberg
por: Mangold, Paul, et al.
Publicado: (2024)

A Study of Condition Numbers for First-Order Optimization
por: Guille-Escuret, Charles, et al.
Publicado: (2020)

Nonsmooth nonconvex stochastic heavy ball
por: Le, Tam
Publicado: (2023)

Gradient Descent on Logistic Regression: Do Large Step-Sizes Work with Data on the Sphere?
por: Meng, Si Yi, et al.
Publicado: (2025)

An adaptive heavy ball method for ill-posed inverse problems
por: Jin, Qinian, et al.
Publicado: (2024)

On adaptive stochastic heavy ball momentum for solving linear systems
por: Zeng, Yun, et al.
Publicado: (2023)

Singular perturbation in heavy ball dynamics
por: Josz, Cedric, et al.
Publicado: (2024)

Convergence analysis of a stochastic heavy-ball method for linear ill-posed problems
por: Jin, Qinian, et al.
Publicado: (2024)

Automated tight Lyapunov analysis for first-order methods
por: Upadhyaya, Manu, et al.
Publicado: (2023)

Proving Linear Mode Connectivity of Neural Networks via Optimal Transport
por: Ferbach, Damien, et al.
Publicado: (2023)

Augmented Lagrangian methods for infeasible convex optimization problems and diverging proximal-point algorithms
por: Andrews, Roland, et al.
Publicado: (2025)

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

The AutoLyap software suite for computer-assisted Lyapunov analyses of first-order methods
por: Upadhyaya, Manu, et al.
Publicado: (2025)

An accelerated proximal bundle method for convex optimization
por: Liao, Feng-Yi, et al.
Publicado: (2025)

A stochastic moving ball approximation method for smooth convex constrained minimization
por: Singh, Nitesh Kumar, et al.
Publicado: (2024)

A heavy-ball type curve search method for smooth convexly constrained optimization
por: Donnini, Federica, et al.
Publicado: (2026)

On the convergence rate of the boosted Difference-of-Convex Algorithm (DCA)
por: Abbaszadehpeivasti, Hadi, et al.
Publicado: (2025)

A constructive approach to strengthen algebraic descriptions of function and operator classes
por: Rubbens, Anne, et al.
Publicado: (2025)

Unifying restart accelerated gradient and proximal bundle methods
por: Liang, Jiaming
Publicado: (2025)

Stochastic dual coordinate descent with adaptive heavy ball momentum for linearly constrained convex optimization
por: Zeng, Yun, et al.
Publicado: (2023)

A new use of the Kurdyka-Lojasiewicz property to study asymptotic behaviours of some stochastic optimization algorithms in a non-convex differentiable framework
por: Fest, Jean-Baptiste
Publicado: (2023)

The stochastic Ravine accelerated gradient method with general extrapolation coefficients
por: Attouch, Hedy, et al.
Publicado: (2024)

Provably data-driven projection method for quadratic programming
por: Nguyen, Anh Tuan, et al.
Publicado: (2025)

A smoothing moving balls approximation method for a class of conic-constrained difference-of-convex optimization problems
por: Xu, Jiefeng, et al.
Publicado: (2025)

Anderson acceleration of derivative-free projection methods for constrained monotone nonlinear equations
por: Jin, Jiachen, et al.
Publicado: (2024)

Continuous and discrete-time accelerated methods for an inequality constrained convex optimization problem
por: Liu, Juan, et al.
Publicado: (2024)

Universal heavy-ball method for nonconvex optimization under Hölder continuous Hessians
por: Marumo, Naoki, et al.
Publicado: (2023)