Cover Image

Second-order methods for provably escaping strict saddle points in composite nonconvex and nonsmooth optimization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bodard, Alexander, Ahookhosh, Masoud, Patrinos, Panagiotis
Format:	Preprint
Published:	2025
Subjects:	Optimization and Control
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

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

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

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

Avoiding strict saddle points of nonconvex regularized problems
by: Bai, Luwei, et al.
Published: (2024)

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

EM++: A parameter learning framework for stochastic switching systems
by: Wang, Renzi, et al.
Published: (2024)

Scaled relative graphs for pairs of operators beyond classical monotonicity
by: Quan, Jan, et al.
Published: (2025)

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

Global Convergence Analysis of the Power Proximal Point and Augmented Lagrangian Method
by: Oikonomidis, Konstantinos A., et al.
Published: (2023)

Nonlinearly preconditioned gradient flows
by: Oikonomidis, Konstantinos, et al.
Published: (2025)

On fundamental properties of high-order forward-backward envelope
by: Kabgani, Alireza, et al.
Published: (2025)

ItsOPT: An inexact two-level smoothing framework for nonconvex optimization via high-order Moreau envelope
by: Kabgani, Alireza, et al.
Published: (2024)

Moreau envelope and proximal-point methods under the lens of high-order regularization
by: Kabgani, Alireza, et al.
Published: (2025)

Randomized coordinate gradient descent almost surely escapes strict saddle points
by: Chen, Ziang, et al.
Published: (2025)

A new envelope function for nonsmooth DC optimization
by: Themelis, Andreas, et al.
Published: (2020)

Stochastic ADMM with batch size adaptation for nonconvex nonsmooth optimization
by: Jin, Jiachen, et al.
Published: (2025)

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

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

An implementable proximal-type method for computing critical points to minimization problems with a nonsmooth and nonconvex constraint
by: Sempere, Gregorio M., et al.
Published: (2024)

Subgradient sampling for nonsmooth nonconvex minimization
by: Bolte, Jérôme, et al.
Published: (2022)

PANOC-lite: A simpler and more efficient algorithm for composite minimization
by: Bodard, Alexander, et al.
Published: (2026)

An inexact $q$-order regularized proximal Newton method for nonconvex composite optimization
by: Liu, Ruyu, et al.
Published: (2023)

Avoidance of non-strict saddle points by blow-up
by: Achour, El Mehdi, et al.
Published: (2025)

Convergence rates for an inexact linearized ADMM for nonsmooth nonconvex optimization with nonlinear equality constraints
by: Bourkhissi, Lahcen El, et al.
Published: (2025)

Variable Bregman Majorization-Minimization algorithms for nonconvex nonsmooth optimization, with application to Poisson imaging
by: Adly, Maxence, et al.
Published: (2026)

An effective subgradient algorithm via Mifflin's line search for nonsmooth nonconvex multiobjective optimization
by: Maleknia, Morteza, et al.
Published: (2024)

A theory on the absence of spurious solutions for nonconvex and nonsmooth optimization
by: Josz, Cedric, et al.
Published: (2018)

Block majorization-minimization with diminishing radius for constrained nonsmooth nonconvex optimization
by: Lyu, Hanbaek, et al.
Published: (2020)

Riemannian trust-region methods for strict saddle functions with complexity guarantees
by: Goyens, Florentin, et al.
Published: (2024)

Simple linesearch-free first-order methods for nonconvex optimization
by: Yagishita, Shotaro, et al.
Published: (2025)

Local adapt-then-combine algorithms for distributed nonsmooth optimization: Achieving provable communication acceleration
by: Guo, Luyao, et al.
Published: (2026)

Minimizing smooth Kurdyka-Łojasiewicz functions via generalized descent methods: Convergence rate and complexity
by: Ahookhosh, Masoud, et al.
Published: (2025)

Phase retrieval via overparametrized nonconvex optimization: nonsmooth amplitude loss landscapes
by: McRae, Andrew D.
Published: (2025)

First-order majorization-minimization meets high-order majorant: Boosted inexact high-order forward-backward method
by: Kabgani, Alireza, et al.
Published: (2025)

Robust Learning Meets Quasar-Convex Optimization: Inexact High-Order Proximal-Point Methods
by: Kabgani, Alireza, et al.
Published: (2026)

Gradient descent provably escapes saddle points in the training of shallow ReLU networks
by: Cheridito, Patrick, et al.
Published: (2022)

On a globally convergent semismooth* Newton method in nonsmooth nonconvex optimization
by: Gfrerer, H.
Published: (2024)

A four-operator splitting algorithm for nonconvex and nonsmooth optimization
by: Alcantara, Jan Harold, et al.
Published: (2024)

Douglas-Rachford splitting and ADMM for nonconvex optimization: Accelerated and Newton-type linesearch algorithms
by: Themelis, Andreas, et al.
Published: (2020)