Copertina

Negative Stepsizes Make Gradient-Descent-Ascent Converge

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Shugart, Henry, Altschuler, Jason M.
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Optimization and Control Data Structures and Algorithms Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Negative Momentum for Convex-Concave Optimization
di: Shugart, Henry, et al.
Pubblicazione: (2026)

Min-Max Optimization Is Strictly Easier Than Variational Inequalities
di: Shugart, Henry, et al.
Pubblicazione: (2025)

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

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

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

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

Optimized methods for composite optimization: a reduction perspective
di: Bok, Jinho, et al.
Pubblicazione: (2025)

Grams: Gradient Descent with Adaptive Momentum Scaling
di: Cao, Yang, et al.
Pubblicazione: (2024)

Gradient Descent is Pareto-Optimal in the Oracle Complexity and Memory Tradeoff for Feasibility Problems
di: Blanchard, Moise
Pubblicazione: (2024)

Gradient Testing and Estimation by Comparisons
di: Tao, Xiwen, et al.
Pubblicazione: (2024)

Gradient-Free Method for Heavily Constrained Nonconvex Optimization
di: Shi, Wanli, et al.
Pubblicazione: (2024)

Convergence analysis of wide shallow neural operators within the framework of Neural Tangent Kernel
di: Xu, Xianliang, et al.
Pubblicazione: (2024)

Online Bilevel Optimization: Regret Analysis of Online Alternating Gradient Methods
di: Tarzanagh, Davoud Ataee, et al.
Pubblicazione: (2022)

Near-Linear Runtime for a Classical Matrix Preconditioning Algorithm
di: Cai, Xufeng, et al.
Pubblicazione: (2025)

Online Convex Optimization with Switching Cost with Only One Single Gradient Evaluation
di: Shah, Harsh, et al.
Pubblicazione: (2025)

Randomized Kaczmarz Methods with Beyond-Krylov Convergence
di: Dereziński, Michał, et al.
Pubblicazione: (2025)

Convex Optimization with Nested Evolving Feasible Sets
di: M., Karthick Krishna, et al.
Pubblicazione: (2026)

Towards Universal Convergence of Backward Error in Linear System Solvers
di: Dereziński, Michał, et al.
Pubblicazione: (2026)

Convergence Analysis of Two-Layer Neural Networks under Gaussian Input Masking
di: Kolomvaki, Afroditi, et al.
Pubblicazione: (2026)

Optimal Bounds for Adversarial Constrained Online Convex Optimization
di: Ferreira, Ricardo N., et al.
Pubblicazione: (2025)

Distributionally Robust Optimization with Adversarial Data Contamination
di: Li, Shuyao, et al.
Pubblicazione: (2025)

Oracle-based Uniform Sampling from Convex Bodies
di: Dang, Thanh, et al.
Pubblicazione: (2025)

Discrete and Continuous Difference of Submodular Minimization
di: Orfanides, George, et al.
Pubblicazione: (2025)

Learning to Schedule in Parallel-Server Queues with Stochastic Bilinear Rewards
di: Kim, Jung-hun, et al.
Pubblicazione: (2021)

Constrained and Composite Sampling via Proximal Sampler
di: Dang, Thanh, et al.
Pubblicazione: (2026)

Importance Sparsification for Sinkhorn Algorithm
di: Li, Mengyu, et al.
Pubblicazione: (2023)

Complexity of Classical Acceleration for $\ell_1$-Regularized PageRank
di: Fountoulakis, Kimon, et al.
Pubblicazione: (2026)

Robust Learning of a Group DRO Neuron
di: Cao, Guyang, et al.
Pubblicazione: (2026)

Online Linear Programming with Replenishment
di: Chen, Yuze, et al.
Pubblicazione: (2026)

Learning-Augmented Algorithms for Online Concave Packing and Convex Covering Problems
di: Grigorescu, Elena, et al.
Pubblicazione: (2024)

Learning Mixtures of Spherical Gaussians via Fourier Analysis
di: Chakraborty, Somnath, et al.
Pubblicazione: (2020)

Gaussian Cooling and Dikin Walks: The Interior-Point Method for Logconcave Sampling
di: Kook, Yunbum, et al.
Pubblicazione: (2023)

Learning-Augmented Algorithms for the Bahncard Problem
di: Zhao, Hailiang, et al.
Pubblicazione: (2024)

Noise Stability Optimization for Finding Flat Minima: A Hessian-based Regularization Approach
di: Zhang, Hongyang R., et al.
Pubblicazione: (2023)

Closing the Computational-Query Depth Gap in Parallel Stochastic Convex Optimization
di: Jambulapati, Arun, et al.
Pubblicazione: (2024)

Non-Stationary Online Resource Allocation: Learning from a Single Sample
di: Feng, Yiding, et al.
Pubblicazione: (2026)

Accelerated Algorithms for Constrained Nonconvex-Nonconcave Min-Max Optimization and Comonotone Inclusion
di: Cai, Yang, et al.
Pubblicazione: (2022)

Optimal Decentralized Smoothed Online Convex Optimization
di: Bhuyan, Neelkamal, et al.
Pubblicazione: (2024)

Learning a Single Neuron Robustly to Distributional Shifts and Adversarial Label Noise
di: Li, Shuyao, et al.
Pubblicazione: (2024)

Extended convexity and smoothness and their applications in deep learning
di: Qi, Binchuan, et al.
Pubblicazione: (2024)