Image de couverture de livre

Newton Method Revisited: Global Convergence Rates up to $\mathcal {O}\left(k^{-3} \right)$ for Stepsize Schedules and Linesearch Procedures

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Hanzely, Slavomír, Abdukhakimov, Farshed, Takáč, Martin
Format:	Preprint
Publié:	2024
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

Polyak Stepsize: Estimating Optimal Functional Values Without Parameters or Prior Knowledge
par: Abdukhakimov, Farshed, et autres
Publié: (2025)

Sketch-and-Project Meets Newton Method: Global $\mathcal O(k^{-2})$ Convergence with Low-Rank Updates
par: Hanzely, Slavomír
Publié: (2023)

Simple Stepsize for Quasi-Newton Methods with Global Convergence Guarantees
par: Agafonov, Artem, et autres
Publié: (2025)

Loss-Transformation Invariance in the Damped Newton Method
par: Shestakov, Alexander, et autres
Publié: (2025)

SANIA: Polyak-type Optimization Framework Leads to Scale Invariant Stochastic Algorithms
par: Abdukhakimov, Farshed, et autres
Publié: (2023)

Preconditioned Norms: A Unified Framework for Steepest Descent, Quasi-Newton and Adaptive Methods
par: Veprikov, Andrey, et autres
Publié: (2025)

$ψ$DAG: Projected Stochastic Approximation Iteration for DAG Structure Learning
par: Ziu, Klea, et autres
Publié: (2024)

Coderivative-Based Newton Methods with Wolfe Linesearch for Nonsmooth Optimization
par: Chao, Miantao, et autres
Publié: (2024)

A Regularized Hessian-Free Inexact Newton-Type Method with Global $\mathcal{O}(k^{-2})$ Convergence
par: Maia, Leandro Farias, et autres
Publié: (2026)

Decentralized Inexact Cubic Newton Method with Consensus Procedure
par: Agafonov, Artem, et autres
Publié: (2026)

OPTAMI: Global Superlinear Convergence of High-order Methods
par: Kamzolov, Dmitry, et autres
Publié: (2024)

LeAP-SSN: A Semismooth Newton Method with Global Convergence Rates
par: Alphonse, Amal, et autres
Publié: (2025)

Linear Convergence Rate in Convex Setup is Possible! Gradient Descent Method Variants under $(L_0,L_1)$-Smoothness
par: Lobanov, Aleksandr, et autres
Publié: (2024)

A Relative Inexact Proximal Gradient Method with an Explicit Linesearch
par: Bello-Cruz, Yunier, et autres
Publié: (2024)

Multilevel Regularized Newton Methods with Fast Convergence Rates
par: Tsipinakis, Nick, et autres
Publié: (2024)

Acceleration by Stepsize Hedging II: Silver Stepsize Schedule for Smooth Convex Optimization
par: Altschuler, Jason M., et autres
Publié: (2023)

Revisiting Superlinear Convergence of Proximal Newton-Like Methods to Degenerate Solutions
par: Lee, Ching-pei, et autres
Publié: (2026)

Adaptive Regularized Newton Method with Inexact Hessian
par: Shestakov, Aleksandr, et autres
Publié: (2025)

An Adaptive Stochastic Gradient Method with Non-negative Gauss-Newton Stepsizes
par: Orvieto, Antonio, et autres
Publié: (2024)

Accelerated Gradient Descent by Concatenation of Stepsize Schedules
par: Zhang, Zehao, et autres
Publié: (2024)

Generalization of Silver Stepsize Schedule to Stochastic Optimization
par: Bai, Luwei, et autres
Publié: (2025)

Composing Optimized Stepsize Schedules for Gradient Descent
par: Grimmer, Benjamin, et autres
Publié: (2024)

Incremental Gauss--Newton Methods with Superlinear Convergence Rates
par: Zhou, Zhiling, et autres
Publié: (2024)

Acceleration by Random Stepsizes: Hedging, Equalization, and the Arcsine Stepsize Schedule
par: Altschuler, Jason M., et autres
Publié: (2024)

Adaptive SGD with Line-Search and Polyak Stepsizes: Nonconvex Convergence and Accelerated Rates
par: Wu, Haotian
Publié: (2025)

Incremental Quasi-Newton Methods with Faster Superlinear Convergence Rates
par: Liu, Zhuanghua, et autres
Publié: (2024)

TRAFS: A Nonsmooth Convex Optimization Algorithm with $\mathcal{O}\left(\frac{1}ε\right)$ Iteration Complexity
par: Jia, Kai, et autres
Publié: (2023)

Acceleration by Stepsize Hedging I: Multi-Step Descent and the Silver Stepsize Schedule
par: Altschuler, Jason M., et autres
Publié: (2023)

Revisiting the Constant Stepsize Stochastic Approximation with Decision-Dependent Markovian Noise
par: Hadavi, Hadi, et autres
Publié: (2026)

Zeroth-order Stochastic Cubic Newton Method Revisited
par: Liu, Yu, et autres
Publié: (2024)

Exploring Jacobian Inexactness in Second-Order Methods for Variational Inequalities: Lower Bounds, Optimal Algorithms and Quasi-Newton Approximations
par: Agafonov, Artem, et autres
Publié: (2024)

Cubic Regularized Newton Method with Variance Reduction for Finite-sum Non-convex Problems
par: Pasechnyuk-Vilensky, Dmitry, et autres
Publié: (2025)

New Results on the Polyak Stepsize: Tight Convergence Analysis and Universal Function Classes
par: He, Chang, et autres
Publié: (2025)

Online Learning Guided Quasi-Newton Methods with Global Non-Asymptotic Convergence
par: Jiang, Ruichen, et autres
Publié: (2024)

Adaptive Multilevel Newton: A Quadratically Convergent Optimization Method
par: Tsipinakis, Nick, et autres
Publié: (2023)

Revisiting LocalSGD and SCAFFOLD: Improved Rates and Missing Analysis
par: Luo, Ruichen, et autres
Publié: (2025)

Dynamics of SGD with Stochastic Polyak Stepsizes: Truly Adaptive Variants and Convergence to Exact Solution
par: Orvieto, Antonio, et autres
Publié: (2022)

Constant Stepsize Q-learning: Distributional Convergence, Bias and Extrapolation
par: Zhang, Yixuan, et autres
Publié: (2024)

Unified Convergence Theory of Stochastic and Variance-Reduced Cubic Newton Methods
par: Chayti, El Mahdi, et autres
Publié: (2023)

Gradient Regularized Newton Boosting Trees with Global Convergence
par: Zozoulenko, Nikita, et autres
Publié: (2026)