Cover Image

A Strengthened Conjecture on the Minimax Optimal Constant Stepsize for Gradient Descent

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Grimmer, Benjamin, Shu, Kevin, Wang, Alex L.
Format:	Preprint
Published:	2024
Subjects:	Optimization and Control
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

Beyond Minimax Optimality: A Subgame Perfect Gradient Method
by: Grimmer, Benjamin, et al.
Published: (2024)

Accelerated Objective Gap and Gradient Norm Convergence for Gradient Descent via Long Steps
by: Grimmer, Benjamin, et al.
Published: (2024)

Provably Faster Gradient Descent via Long Steps
by: Grimmer, Benjamin
Published: (2023)

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

On Averaging and Extrapolation for Gradient Descent
by: Luner, Alan, et al.
Published: (2024)

Subgame Perfect Methods in Nonsmooth Convex Optimization
by: Grimmer, Benjamin, et al.
Published: (2025)

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

A Practical Adaptive Subgame Perfect Gradient Method
by: Luner, Alan, et al.
Published: (2025)

Accelerating Proximal Gradient Descent via Silver Stepsizes
by: Bok, Jinho, et al.
Published: (2024)

Stepsize Hedging: an Alternative Mechanism for Accelerating Gradient Descent
by: Altschuler, Jason M., et al.
Published: (2026)

Inexactly Smooth Performance Estimation and New Optimized Gradient Methods
by: Zoll, Aaron, et al.
Published: (2026)

A Universally Optimal Primal-Dual Method for Minimizing Heterogeneous Compositions
by: Zoll, Aaron, et al.
Published: (2025)

The Optimal Smoothings of Sublinear Functions and Convex Cones
by: Samakhoana, Thabo, et al.
Published: (2025)

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

Negative Stepsizes Make Gradient-Descent-Ascent Converge
by: Shugart, Henry, et al.
Published: (2025)

On Gradient Descent Ascent for Nonconvex-Concave Minimax Problems
by: Lin, Tianyi, et al.
Published: (2019)

Det-CGD: Compressed Gradient Descent with Matrix Stepsizes for Non-Convex Optimization
by: Li, Hanmin, et al.
Published: (2023)

Large Stepsize Gradient Descent for Non-Homogeneous Two-Layer Networks: Margin Improvement and Fast Optimization
by: Cai, Yuhang, et al.
Published: (2024)

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

Achieving Near-Optimal Convergence for Distributed Minimax Optimization with Adaptive Stepsizes
by: Huang, Yan, et al.
Published: (2024)

Revisiting the Constant Stepsize Stochastic Approximation with Decision-Dependent Markovian Noise
by: Hadavi, Hadi, et al.
Published: (2026)

Two-Timescale Gradient Descent Ascent Algorithms for Nonconvex Minimax Optimization
by: Lin, Tianyi, et al.
Published: (2024)

Decentralized Stochastic Gradient Descent Ascent for Finite-Sum Minimax Problems
by: Gao, Hongchang
Published: (2022)

A Parameter-Free Restart Scheme with Only a Parallelizable $\log\log(1/ε)$ Overhead
by: Wu, Yue, et al.
Published: (2026)

A Mean-Field Analysis of Neural Stochastic Gradient Descent-Ascent for Functional Minimax Optimization
by: Zhu, Yuchen, et al.
Published: (2024)

An Elementary Proof of the Near Optimality of LogSumExp Smoothing
by: Samakhoana, Thabo, et al.
Published: (2025)

Some Unified Theory for Variance Reduced Prox-Linear Methods
by: Wu, Yue, et al.
Published: (2024)

Scalable Projection-Free Optimization Methods via MultiRadial Duality Theory
by: Samakhoana, Thabo, et al.
Published: (2024)

Lower Bounds for Linear Minimization Oracle Methods Optimizing over Strongly Convex Sets
by: Grimmer, Benjamin, et al.
Published: (2026)

First-Order Methods for Nonsmooth Nonconvex Functional Constrained Optimization with or without Slater Points
by: Jia, Zhichao, et al.
Published: (2022)

Goldstein Stationarity in Lipschitz Constrained Optimization
by: Grimmer, Benjamin, et al.
Published: (2023)

Stochastic Smoothed Gradient Descent Ascent for Federated Minimax Optimization
by: Shen, Wei, et al.
Published: (2023)

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

Bias and Extrapolation in Markovian Linear Stochastic Approximation with Constant Stepsizes
by: Huo, Dongyan, et al.
Published: (2022)

AdGT: Decentralized Gradient Tracking with Tuning-free Per-Agent Stepsize
by: Ghaderyan, Diyako, et al.
Published: (2025)

The Collusion of Memory and Nonlinearity in Stochastic Approximation With Constant Stepsize
by: Huo, Dongyan, et al.
Published: (2024)

AGDA+: Proximal Alternating Gradient Descent Ascent Method with a Nonmonotone Adaptive Step-Size Search for Nonconvex Minimax Problems
by: Zhang, Xuan, 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)

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