Copertina

A Parameter-Free Restart Scheme with Only a Parallelizable $\log\log(1/ε)$ Overhead

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wu, Yue, Grimmer, Benjamin
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Optimization and Control
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

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

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

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

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

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

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

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

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

Restart-Free (Accelerated) Gradient Sliding Methods for Strongly Convex Composite Optimization
di: Wu, Xinming, et al.
Pubblicazione: (2026)

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

Provably Faster Gradient Descent via Long Steps
di: Grimmer, Benjamin
Pubblicazione: (2023)

Some Primal-Dual Theory for Subgradient Methods for Strongly Convex Optimization
di: Grimmer, Benjamin, et al.
Pubblicazione: (2023)

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

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

Optimal Restart Strategies for Parameter-dependent Optimization Algorithms
di: Schönenberger, Lisa, et al.
Pubblicazione: (2025)

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

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

H-invariance theory: A complete characterization of minimax optimal fixed-point algorithms
di: Yoon, TaeHo, et al.
Pubblicazione: (2025)

Restarted Halpern PDHG for Linear Programming
di: Lu, Haihao, et al.
Pubblicazione: (2024)

Polynomial and Parallelizable Preconditioning for Block Tridiagonal Positive Definite Matrices
di: Yang, Shaohui, et al.
Pubblicazione: (2025)

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

Decentralized Concurrent Learning with Coordinated Momentum and Restart
di: Ochoa, Daniel E., et al.
Pubblicazione: (2024)

An Adaptive Parameter-free and Projection-free Restarting Level Set Method for Constrained Convex Optimization Under the Error Bound Condition
di: Lin, Qihang, et al.
Pubblicazione: (2020)

Adaptive Acceleration Without Strong Convexity Priors Or Restarts
di: Cavalcanti, Joao V., et al.
Pubblicazione: (2025)

Almost-sharp $O(k^{-1} \log k)$ convergence rate for the Sinkhorn algorithm in the asymptotically scalable case
di: Wang, Guillaume
Pubblicazione: (2026)

Importance sampling-based gradient method for dimension reduction in Poisson log-normal model
di: Batardière, Bastien, et al.
Pubblicazione: (2024)

Parallelizable Parametric Nonlinear System Identification via tuning of a Moving Horizon State Estimator
di: Simpson, Léo, et al.
Pubblicazione: (2024)

Parallelizable Riemannian Alternating Direction Method of Multipliers for Non-convex Pose Graph Optimization
di: Chen, Xin, et al.
Pubblicazione: (2026)

Accessible Complexity Bounds for Restarted PDHG on Linear Programs with a Unique Optimizer
di: Xiong, Zikai
Pubblicazione: (2024)

Restarted contractive operators to learn at equilibrium
di: Davy, Leo, et al.
Pubblicazione: (2025)

High-Probability Polynomial-Time Complexity of Restarted PDHG for Linear Programming
di: Xiong, Zikai
Pubblicazione: (2025)

A Parameter-Free First-Order Algorithm for Non-Convex Optimization with $\tilde{\mkern1mu O}(ε^{-5/3})$ Global Rate
di: Xiong, Sichao, et al.
Pubblicazione: (2026)

A Parallelizable Quaternion Higher-Order Singular Value Decomposition with Applications
di: Ya, Hanxin, et al.
Pubblicazione: (2023)

A Parameter-Free Stochastic LineseArch Method (SLAM) for Minimizing Expectation Residuals
di: Wang, Qi, et al.
Pubblicazione: (2025)

Robust Accelerated Dynamics for Subnetwork Bilinear Zero-Sum Games with Distributed Restarting
di: Li, Weijian, et al.
Pubblicazione: (2025)

On the Relation Between LP Sharpness and Limiting Error Ratio and Complexity Implications for Restarted PDHG
di: Xiong, Zikai, et al.
Pubblicazione: (2023)

Restarted Primal-Dual Hybrid Conjugate Gradient Method for Large-Scale Quadratic Programming
di: Huang, Yicheng, et al.
Pubblicazione: (2024)

Computational Guarantees for Restarted PDHG for LP based on "Limiting Error Ratios" and LP Sharpness
di: Xiong, Zikai, et al.
Pubblicazione: (2023)

$\texttt{immrax}$: A Parallelizable and Differentiable Toolbox for Interval Analysis and Mixed Monotone Reachability in JAX
di: Harapanahalli, Akash, et al.
Pubblicazione: (2024)