Image de couverture de livre

Escaping saddle points without Lipschitz smoothness: the power of nonlinear preconditioning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Bodard, Alexander, Patrinos, Panagiotis
Format:	Preprint
Publié:	2025
Sujets:	Optimization and Control
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Newton methods beyond Hessian Lipschitz continuity: A nonlinear preconditioning approach
par: Bodard, Alexander, et autres
Publié: (2026)

Second-order methods for provably escaping strict saddle points in composite nonconvex and nonsmooth optimization
par: Bodard, Alexander, et autres
Publié: (2025)

Nonlinearly preconditioned gradient flows
par: Oikonomidis, Konstantinos, et autres
Publié: (2025)

The inexact power augmented Lagrangian method for constrained nonconvex optimization
par: Bodard, Alexander, et autres
Publié: (2024)

EM++: A parameter learning framework for stochastic switching systems
par: Wang, Renzi, et autres
Publié: (2024)

Scaled relative graphs for pairs of operators beyond classical monotonicity
par: Quan, Jan, et autres
Publié: (2025)

Global Convergence Analysis of the Power Proximal Point and Augmented Lagrangian Method
par: Oikonomidis, Konstantinos A., et autres
Publié: (2023)

Dualities for non-Euclidean smoothness and strong convexity under the light of generalized conjugacy
par: Laude, Emanuel, et autres
Publié: (2021)

The Mirror-Prox Sliding Method for Non-smooth decentralized saddle-point problems
par: Kuruzov, Ilya, et autres
Publié: (2022)

Eigenvalue bounds for preconditioned symmetric multiple saddle-point matrices
par: Bergamaschi, L., et autres
Publié: (2025)

A stochastic preconditioned Douglas-Rachford splitting method for saddle-point problems
par: Dong, Yakun, et autres
Publié: (2022)

PANOC-lite: A simpler and more efficient algorithm for composite minimization
par: Bodard, Alexander, et autres
Publié: (2026)

Anisotropic Proximal Point Algorithm
par: Laude, Emanuel, et autres
Publié: (2023)

Anisotropic Proximal Gradient
par: Laude, Emanuel, et autres
Publié: (2022)

Proximal gradient descent on the smoothed duality gap to solve saddle point problems
par: Fercoq, Olivier
Publié: (2025)

Risk-Sensitive Model Predictive Control for Interaction-Aware Planning -- A Sequential Convexification Algorithm
par: Wang, Renzi, et autres
Publié: (2025)

Probabilistic Safety under Arbitrary Disturbance Distributions using Piecewise-Affine Control Barrier Functions
par: Teuwen, Matisse, et autres
Publié: (2025)

Nonlinearly Preconditioned Gradient Methods: Momentum and Stochastic Analysis
par: Oikonomidis, Konstantinos, et autres
Publié: (2025)

Tight Analysis of Difference-of-Convex Algorithm (DCA) Improves Convergence Rates for Proximal Gradient Descent
par: Rotaru, Teodor, et autres
Publié: (2025)

Forward-backward splitting under the light of generalized convexity
par: Oikonomidis, Konstantinos, et autres
Publié: (2025)

Exact worst-case convergence rates of gradient descent: a complete analysis for all constant stepsizes over nonconvex and convex functions
par: Rotaru, Teodor, et autres
Publié: (2024)

On the Regularity of Generalized Conjugate Functions
par: Oikonomidis, Konstantinos, et autres
Publié: (2026)

Improved convergence rates for the Difference-of-Convex algorithm
par: Rotaru, Teodor, et autres
Publié: (2024)

A localized consensus-based sampling algorithm
par: Bouillon, Arne, et autres
Publié: (2025)

Gradient-free algorithm for saddle point problems under overparametrization
par: Statkevich, Ekaterina, et autres
Publié: (2024)

Contractivity and linear convergence in bilinear saddle-point problems: An operator-theoretic approach
par: Dirren, Colin, et autres
Publié: (2024)

Parametric Nonconvex Optimization via Convex Surrogates
par: Wang, Renzi, et autres
Publié: (2026)

Gauss-Newton meets PANOC: A fast and globally convergent algorithm for nonlinear optimal control
par: Pas, Pieter, et autres
Publié: (2022)

Blocked Cholesky factorization updates of the Riccati recursion using hyperbolic Householder transformations
par: Pas, Pieter, et autres
Publié: (2025)

Bregman Finito/MISO for nonconvex regularized finite sum minimization without Lipschitz gradient continuity
par: Latafat, Puya, et autres
Publié: (2021)

Nonlinearly Preconditioned Gradient Methods under Generalized Smoothness
par: Oikonomidis, Konstantinos, et autres
Publié: (2025)

Tight Convergence Rates in Gradient Mapping for the Difference-of-Convex Algorithm
par: Rotaru, Teodor, et autres
Publié: (2025)

Rethinking PCA Through Duality
par: Quan, Jan, et autres
Publié: (2025)

Real-time MPC with Control Barrier Functions for Autonomous Driving using Safety Enhanced Collocation
par: Allamaa, Jean Pierre, et autres
Publié: (2024)

Complexity of Linearized Perturbed Augmented Lagrangian Methods for Nonsmooth Nonconvex Optimization with Nonlinear Equality Constraints
par: Bourkhissi, Lahcen El, et autres
Publié: (2025)

Anderson Accelerated Feasible Sequential Linear Programming
par: Kiessling, David, et autres
Publié: (2022)

An Efficient Mixed-Integer Formulation and an Iterative Method for Optimal Control of Switched Systems Under Dwell Time Constraints
par: Abbasi-Esfeden, Ramin, et autres
Publié: (2025)

Defining Lyapunov functions as the solution of a performance estimation saddle point problem
par: Fercoq, Olivier
Publié: (2024)

Avoidance of non-strict saddle points by blow-up
par: Achour, El Mehdi, et autres
Publié: (2025)

Dealing with unbounded gradients in stochastic saddle-point optimization
par: Neu, Gergely, et autres
Publié: (2024)