Image de couverture de livre

Fast Last-Iterate Convergence of SGD in the Smooth Interpolation Regime

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Attia, Amit, Schliserman, Matan, Sherman, Uri, Koren, Tomer
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Optimization and Control
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Convergence of Policy Mirror Descent Beyond Compatible Function Approximation
par: Sherman, Uri, et autres
Publié: (2025)

Convergence and Sample Complexity of First-Order Methods for Agnostic Reinforcement Learning
par: Sherman, Uri, et autres
Publié: (2025)

Learning Rate Annealing Improves Tuning Robustness in Stochastic Optimization
par: Attia, Amit, et autres
Publié: (2025)

How Free is Parameter-Free Stochastic Optimization?
par: Attia, Amit, et autres
Publié: (2024)

The Dimension Strikes Back with Gradients: Generalization of Gradient Methods in Stochastic Convex Optimization
par: Schliserman, Matan, et autres
Publié: (2024)

Faster Stochastic Optimization with Arbitrary Delays via Asynchronous Mini-Batching
par: Attia, Amit, et autres
Publié: (2024)

Optimal Rates in Continual Linear Regression via Increasing Regularization
par: Levinstein, Ran, et autres
Publié: (2025)

Last-Iterate Convergence of Randomized Kaczmarz and SGD with Greedy Step Size
par: Dereziński, Michał, et autres
Publié: (2026)

Multiclass Loss Geometry Matters for Generalization of Gradient Descent in Separable Classification
par: Schliserman, Matan, et autres
Publié: (2025)

Complexity of Vector-valued Prediction: From Linear Models to Stochastic Convex Optimization
par: Schliserman, Matan, et autres
Publié: (2024)

From Continual Learning to SGD and Back: Better Rates for Continual Linear Models
par: Evron, Itay, et autres
Publié: (2025)

Diagonalisation SGD: Fast & Convergent SGD for Non-Differentiable Models via Reparameterisation and Smoothing
par: Wagner, Dominik, et autres
Publié: (2024)

Towards Fully Parameter-Free Stochastic Optimization: Grid Search with Self-Bounding Analysis
par: Zhao, Yuheng, et autres
Publié: (2026)

On the Last-Iterate Convergence of Shuffling Gradient Methods
par: Liu, Zijian, et autres
Publié: (2024)

Convergence Rate of the Last Iterate of Stochastic Proximal Algorithms
par: Vaidyan, Kevin Kurian Thomas, et autres
Publié: (2026)

Revisiting the Last-Iterate Convergence of Stochastic Gradient Methods
par: Liu, Zijian, et autres
Publié: (2023)

Last Iterate Convergence of Incremental Methods and Applications in Continual Learning
par: Cai, Xufeng, et autres
Publié: (2024)

Convergence of Clipped-SGD for Convex $(L_0,L_1)$-Smooth Optimization with Heavy-Tailed Noise
par: Chezhegov, Savelii, et autres
Publié: (2025)

Improved Last-Iterate Convergence of Shuffling Gradient Methods for Nonsmooth Convex Optimization
par: Liu, Zijian, et autres
Publié: (2025)

Last-Iterate Complexity of SGD for Convex and Smooth Stochastic Problems
par: Garrigos, Guillaume, et autres
Publié: (2025)

Fast Last-Iterate Convergence of Learning in Games Requires Forgetful Algorithms
par: Cai, Yang, et autres
Publié: (2024)

Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs
par: Ding, Dongsheng, et autres
Publié: (2023)

Rapid Overfitting of Multi-Pass Stochastic Gradient Descent in Stochastic Convex Optimization
par: Vansover-Hager, Shira, et autres
Publié: (2025)

Flat Minima and Generalization: Insights from Stochastic Convex Optimization
par: Schliserman, Matan, et autres
Publié: (2025)

Faster Convergence of Local SGD for Over-Parameterized Models
par: Qin, Tiancheng, et autres
Publié: (2022)

Global Convergence of SGD On Two Layer Neural Nets
par: Gopalani, Pulkit, et autres
Publié: (2022)

From PowerSGD to PowerSGD+: Low-Rank Gradient Compression for Distributed Optimization with Convergence Guarantees
par: Xie, Shengping, et autres
Publié: (2025)

On the Interpolation Effect of Score Smoothing in Diffusion Models
par: Chen, Zhengdao
Publié: (2025)

On Separation Between Best-Iterate, Random-Iterate, and Last-Iterate Convergence of Learning in Games
par: Cai, Yang, et autres
Publié: (2025)

VAMO: Efficient Zeroth-Order Variance Reduction for SGD with Faster Convergence
par: Chen, Jiahe, et autres
Publié: (2025)

A Comprehensive Framework for Analyzing the Convergence of Adam: Bridging the Gap with SGD
par: Jin, Ruinan, et autres
Publié: (2024)

Global Convergence of SGD For Logistic Loss on Two Layer Neural Nets
par: Gopalani, Pulkit, et autres
Publié: (2023)

On the Convergence of DP-SGD with Adaptive Clipping
par: Shulgin, Egor, et autres
Publié: (2024)

Gradient Descent's Last Iterate is Often (slightly) Suboptimal
par: Kornowski, Guy, et autres
Publié: (2026)

Differentially Private Clipped-SGD: High-Probability Convergence with Arbitrary Clipping Level
par: Khah, Saleh Vatan, et autres
Publié: (2025)

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

Convergence of SGD with momentum in the nonconvex case: A time window-based analysis
par: Qiu, Junwen, et autres
Publié: (2024)

Convergence and concentration properties of constant step-size SGD through Markov chains
par: Merad, Ibrahim, et autres
Publié: (2023)

From Average-Iterate to Last-Iterate Convergence in Games: A Reduction and Its Applications
par: Cai, Yang, et autres
Publié: (2025)

Convergence of SGD for Training Neural Networks with Sliced Wasserstein Losses
par: Tanguy, Eloi
Publié: (2023)