Copertina

New Results on the Polyak Stepsize: Tight Convergence Analysis and Universal Function Classes

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	He, Chang, Gao, Wenzhi, Jiang, Bo, Udell, Madeleine, Zhang, Shuzhong
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Optimization and Control
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Small Gradient Norm Regret for Online Convex Optimization
di: Gao, Wenzhi, et al.
Pubblicazione: (2026)

New Perspectives on the Polyak Stepsize: Surrogate Functions and Negative Results
di: Orabona, Francesco, et al.
Pubblicazione: (2025)

When Does Primal Interior Point Method Beat Primal-dual in Linear Optimization?
di: Gao, Wenzhi, et al.
Pubblicazione: (2024)

Accelerating Level-Value Adjustment for the Polyak Stepsize
di: Liu, Anbang, et al.
Pubblicazione: (2023)

Dynamics of SGD with Stochastic Polyak Stepsizes: Truly Adaptive Variants and Convergence to Exact Solution
di: Orvieto, Antonio, et al.
Pubblicazione: (2022)

Scalable Approximate Optimal Diagonal Preconditioning
di: Gao, Wenzhi, et al.
Pubblicazione: (2023)

Polyak Stepsize: Estimating Optimal Functional Values Without Parameters or Prior Knowledge
di: Abdukhakimov, Farshed, et al.
Pubblicazione: (2025)

Non-Stationary Bandit Convex Optimization: An Optimal Algorithm with Two-Point Feedback
di: He, Chang, et al.
Pubblicazione: (2025)

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

Gradient Methods with Online Scaling Part I. Theoretical Foundations
di: Gao, Wenzhi, et al.
Pubblicazione: (2025)

Provable and Practical Online Learning Rate Adaptation with Hypergradient Descent
di: Chu, Ya-Chi, et al.
Pubblicazione: (2025)

Gradient Methods with Online Scaling Part II. Practical Aspects
di: Chu, Ya-Chi, et al.
Pubblicazione: (2025)

Gradient Methods with Online Scaling
di: Gao, Wenzhi, et al.
Pubblicazione: (2024)

Adaptive Polyak Stepsize with Level-value Adjustment for Distributed Optimization
di: Ouyang, Chen, et al.
Pubblicazione: (2026)

Algebraic characterization of equivalence between oracle-based iterative algorithms
di: Lessard, Laurent, et al.
Pubblicazione: (2025)

History-Aware Adaptive High-Order Tensor Regularization
di: He, Chang, et al.
Pubblicazione: (2025)

On Relatively Smooth Optimization over Riemannian Manifolds
di: He, Chang, et al.
Pubblicazione: (2025)

On the Nature of Regularity Assumptions in Bilevel Optimization with Constrained Lower-level Problem
di: Jiang, Xiaotian, et al.
Pubblicazione: (2026)

An automatic system to detect equivalence between iterative algorithms
di: Zhao, Shipu, et al.
Pubblicazione: (2021)

Linear Convergence of the Proximal Gradient Method for Composite Optimization Under the Polyak-Łojasiewicz Inequality and Its Variant
di: Kong, Qingyuan, et al.
Pubblicazione: (2024)

Natural Hypergradient Descent: Algorithm Design, Convergence Analysis, and Parallel Implementation
di: Kong, Deyi, et al.
Pubblicazione: (2026)

On the (linear) convergence of Generalized Newton Inexact ADMM
di: Frangella, Zachary, et al.
Pubblicazione: (2023)

Accelerated Gradient Descent by Concatenation of Stepsize Schedules
di: Zhang, Zehao, et al.
Pubblicazione: (2024)

Complexity Analysis of Convex Majorization Schemes for Nonconvex Constrained Optimization
di: Wang, Nuozhou, et al.
Pubblicazione: (2025)

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

Constant Stepsize Q-learning: Distributional Convergence, Bias and Extrapolation
di: Zhang, Yixuan, et al.
Pubblicazione: (2024)

"It Was a Magical Box": Understanding Practitioner Workflows and Needs in Optimization
di: Lawless, Connor, et al.
Pubblicazione: (2025)

Universality of AdaGrad Stepsizes for Stochastic Optimization: Inexact Oracle, Acceleration and Variance Reduction
di: Rodomanov, Anton, et al.
Pubblicazione: (2024)

Beyond Nonconvexity: A Universal Trust-Region Method with New Analyses
di: Jiang, Yuntian, et al.
Pubblicazione: (2023)

GeNIOS: an (almost) second-order operator-splitting solver for large-scale convex optimization
di: Diamandis, Theo, et al.
Pubblicazione: (2023)

SketchySGD: Reliable Stochastic Optimization via Randomized Curvature Estimates
di: Frangella, Zachary, et al.
Pubblicazione: (2022)

PROMISE: Preconditioned Stochastic Optimization Methods by Incorporating Scalable Curvature Estimates
di: Frangella, Zachary, et al.
Pubblicazione: (2023)

New Classes of Non-monotone Variational Inequality Problems Solvable via Proximal Gradient on Smooth Gap Functions
di: Zhao, Lei, et al.
Pubblicazione: (2025)

Acceleration for Polyak-Łojasiewicz Functions with a Gradient Aiming Condition
di: Hermant, Julien
Pubblicazione: (2026)

Simple Stepsize for Quasi-Newton Methods with Global Convergence Guarantees
di: Agafonov, Artem, et al.
Pubblicazione: (2025)

Acceleration by Stepsize Hedging II: Silver Stepsize Schedule for Smooth Convex Optimization
di: Altschuler, Jason M., et al.
Pubblicazione: (2023)

Quantized Distributed Nonconvex Optimization Algorithms with Linear Convergence under the Polyak--$Ł$ojasiewicz Condition
di: Xu, Lei, et al.
Pubblicazione: (2022)

Stochastic Block Bregman Projection with Polyak-like Stepsize for Possibly Inconsistent Convex Feasibility Problems
di: Zhang, Lu, et al.
Pubblicazione: (2026)

Stochastic Polyak Step-sizes and Momentum: Convergence Guarantees and Practical Performance
di: Oikonomou, Dimitris, et al.
Pubblicazione: (2024)

Coupling-based Convergence Diagnostic and Stepsize Scheme for Stochastic Gradient Descent
di: Li, Xiang, et al.
Pubblicazione: (2024)