Cover Image

Polyak Stepsize: Estimating Optimal Functional Values Without Parameters or Prior Knowledge

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Abdukhakimov, Farshed, Pham, Cuong Anh, Horváth, Samuel, Takáč, Martin, Hanzely, Slavomır
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

Newton Method Revisited: Global Convergence Rates up to $\mathcal {O}\left(k^{-3} \right)$ for Stepsize Schedules and Linesearch Procedures
by: Hanzely, Slavomír, et al.
Published: (2024)

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

SANIA: Polyak-type Optimization Framework Leads to Scale Invariant Stochastic Algorithms
by: Abdukhakimov, Farshed, et al.
Published: (2023)

Loss-Transformation Invariance in the Damped Newton Method
by: Shestakov, Alexander, et al.
Published: (2025)

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

Preconditioned Norms: A Unified Framework for Steepest Descent, Quasi-Newton and Adaptive Methods
by: Veprikov, Andrey, et al.
Published: (2025)

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

$ψ$DAG: Projected Stochastic Approximation Iteration for DAG Structure Learning
by: Ziu, Klea, et al.
Published: (2024)

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

New Results on the Polyak Stepsize: Tight Convergence Analysis and Universal Function Classes
by: He, Chang, et al.
Published: (2025)

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

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

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

Federated Learning Can Find Friends That Are Advantageous
by: Tupitsa, Nazarii, et al.
Published: (2024)

LoFT: Low-Rank Adaptation That Behaves Like Full Fine-Tuning
by: Tastan, Nurbek, et al.
Published: (2025)

Gradient Clipping Beyond Vector Norms: A Spectral Approach for Matrix-Valued Parameters
by: Yukhimchuk, Alexander, et al.
Published: (2026)

Block Acceleration Without Momentum: On Optimal Stepsizes of Block Gradient Descent for Least-Squares
by: Peng, Liangzu, et al.
Published: (2024)

Revisiting LocalSGD and SCAFFOLD: Improved Rates and Missing Analysis
by: Luo, Ruichen, et al.
Published: (2025)

Parameter-free Clipped Gradient Descent Meets Polyak
by: Takezawa, Yuki, et al.
Published: (2024)

Stochastic Approximation with Block Coordinate Optimal Stepsizes
by: Jiang, Tao, et al.
Published: (2025)

A Strengthened Conjecture on the Minimax Optimal Constant Stepsize for Gradient Descent
by: Grimmer, Benjamin, et al.
Published: (2024)

The Popov's Algorithm with Optimal Bounded Stepsize for Generalized Monotone Variational Inequalities
by: Nguyen, Nhung Hong, et al.
Published: (2026)

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

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

Methods for Convex $(L_0,L_1)$-Smooth Optimization: Clipping, Acceleration, and Adaptivity
by: Gorbunov, Eduard, et al.
Published: (2024)

Methods with Local Steps and Random Reshuffling for Generally Smooth Non-Convex Federated Optimization
by: Demidovich, Yury, et al.
Published: (2024)

Remove that Square Root: A New Efficient Scale-Invariant Version of AdaGrad
by: Choudhury, Sayantan, et al.
Published: (2024)

Polyak Minorant Method for Convex Optimization
by: Devanathan, Nikhil, et al.
Published: (2023)

Approximate Solution Methods for the Average Reward Criterion in Optimal Tracking Control of Linear Systems
by: Nguyen, Duc Cuong
Published: (2025)

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

Clipping Improves Adam-Norm and AdaGrad-Norm when the Noise Is Heavy-Tailed
by: Chezhegov, Savelii, et al.
Published: (2024)

Generalization of Silver Stepsize Schedule to Stochastic Optimization
by: Bai, Luwei, et al.
Published: (2025)

Adaptive Stepsize Selection in Decentralized Convex Optimization
by: Kuruzov, Ilya, et al.
Published: (2025)

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

Composing Optimized Stepsize Schedules for Gradient Descent
by: Grimmer, Benjamin, et al.
Published: (2024)

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

Random-reshuffled SARAH does not need a full gradient computations
by: Beznosikov, Aleksandr, et al.
Published: (2021)

Genericity of Polyak-Lojasiewicz Inequalities for Entropic Mean-Field Neural ODEs
by: Daudin, Samuel, et al.
Published: (2025)

Minimisation of Polyak-Łojasewicz Functions Using Random Zeroth-Order Oracles
by: Farzin, Amir Ali, et al.
Published: (2024)

Safeguarded Stochastic Polyak Step Sizes for Non-smooth Optimization: Robust Performance Without Small (Sub)Gradients
by: Oikonomou, Dimitris, et al.
Published: (2025)