Image de couverture de livre

ROOT-SGD: Sharp Nonasymptotics and Near-Optimal Asymptotics in a Single Algorithm

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Li, Chris Junchi, Mou, Wenlong, Wainwright, Martin J., Jordan, Michael I.
Format:	Preprint
Publié:	2020
Sujets:	Optimization and Control Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Enhancing Stochastic Optimization for Statistical Efficiency Using ROOT-SGD with Diminishing Stepsize
par: Li, Chris Junchi
Publié: (2024)

Optimal and instance-dependent guarantees for Markovian linear stochastic approximation
par: Mou, Wenlong, et autres
Publié: (2021)

A General Continuous-Time Formulation of Stochastic ADMM and Its Variants
par: Li, Chris Junchi
Publié: (2024)

Accelerated Fully First-Order Methods for Bilevel and Minimax Optimization
par: Li, Chris Junchi
Publié: (2024)

Does SGD Seek Flatness or Sharpness? An Exactly Solvable Model
par: Xu, Yizhou, et autres
Publié: (2026)

Continuous-time reinforcement learning: ellipticity enables model-free value function approximation
par: Mou, Wenlong
Publié: (2026)

Optimal Guarantees for Algorithmic Reproducibility and Gradient Complexity in Convex Optimization
par: Zhang, Liang, et autres
Publié: (2023)

An Optimistic Algorithm for Online Convex Optimization with Adversarial Constraints
par: Lekeufack, Jordan, et autres
Publié: (2024)

SGD at the Edge of Stability: The Stochastic Sharpness Gap
par: Liao, Fangshuo, et autres
Publié: (2026)

Statistical guarantees for continuous-time policy evaluation: blessing of ellipticity and new tradeoffs
par: Mou, Wenlong
Publié: (2025)

Is RL fine-tuning harder than regression? A PDE learning approach for diffusion models
par: Mou, Wenlong
Publié: (2025)

Convergence of Gradient Descent for Recurrent Neural Networks: A Nonasymptotic Analysis
par: Cayci, Semih, et autres
Publié: (2024)

A Nearly Optimal Single Loop Algorithm for Stochastic Bilevel Optimization under Unbounded Smoothness
par: Gong, Xiaochuan, et autres
Publié: (2024)

Shadowheart SGD: Distributed Asynchronous SGD with Optimal Time Complexity Under Arbitrary Computation and Communication Heterogeneity
par: Tyurin, Alexander, et autres
Publié: (2024)

Sharp High-Probability Rates for Nonlinear SGD under Heavy-Tailed Noise via Symmetrization
par: Armacki, Aleksandar, et autres
Publié: (2025)

The Optimality of (Accelerated) SGD for High-Dimensional Quadratic Optimization
par: Zhang, Haihan, et autres
Publié: (2024)

Optimal Projection-Free Adaptive SGD for Matrix Optimization
par: Kovalev, Dmitry
Publié: (2026)

A Near-Optimal Single-Loop Stochastic Algorithm for Convex Finite-Sum Coupled Compositional Optimization
par: Wang, Bokun, et autres
Publié: (2023)

Perseus: A Simple and Optimal High-Order Method for Variational Inequalities
par: Lin, Tianyi, et autres
Publié: (2022)

Accelerating Single-Pass SGD for Generalized Linear Prediction
par: Chen, Qian, et autres
Publié: (2026)

TiAda: A Time-scale Adaptive Algorithm for Nonconvex Minimax Optimization
par: Li, Xiang, et autres
Publié: (2022)

Taming "data-hungry" reinforcement learning? Stability in continuous state-action spaces
par: Duan, Yaqi, et autres
Publié: (2024)

On the Provable Suboptimality of Momentum SGD in Nonstationary Stochastic Optimization
par: Sahu, Sharan, et autres
Publié: (2026)

Near-Optimal Algorithms for Group Distributionally Robust Optimization and Beyond
par: Soma, Tasuku, et autres
Publié: (2022)

Bias-Optimal Bounds for SGD: A Computer-Aided Lyapunov Analysis
par: Cortild, Daniel, et autres
Publié: (2025)

Asymptotically Optimal Regret for Black-Box Predict-then-Optimize
par: Tan, Samuel, et autres
Publié: (2024)

A Specialized Semismooth Newton Method for Kernel-Based Optimal Transport
par: Lin, Tianyi, et autres
Publié: (2023)

Two-Timescale Gradient Descent Ascent Algorithms for Nonconvex Minimax Optimization
par: Lin, Tianyi, et autres
Publié: (2024)

Nonasymptotic Convergence Rates for Plug-and-Play Methods With MMSE Denoisers
par: Pritchard, Henry, et autres
Publié: (2025)

On Bellman equations for continuous-time policy evaluation I: discretization and approximation
par: Mou, Wenlong, et autres
Publié: (2024)

Exploiting Exogenous Structure for Sample-Efficient Reinforcement Learning
par: Wan, Jia, et autres
Publié: (2024)

Optimal Growth Schedules for Batch Size and Learning Rate in SGD that Reduce SFO Complexity
par: Umeda, Hikaru, et autres
Publié: (2025)

Nonasymptotic analysis of Stochastic Gradient Hamiltonian Monte Carlo under local conditions for nonconvex optimization
par: Akyildiz, Ömer Deniz, et autres
Publié: (2020)

A Minibatch-SGD-Based Learning Meta-Policy for Inventory Systems with Myopic Optimal Policy
par: Lyu, Jiameng, et autres
Publié: (2024)

Near-Optimal Primal-Dual Algorithm for Learning Linear Mixture CMDPs with Adversarial Rewards
par: Yu, Kihyun, et autres
Publié: (2026)

A Lower Bound and a Near-Optimal Algorithm for Bilevel Empirical Risk Minimization
par: Dagréou, Mathieu, et autres
Publié: (2023)

A Nearly Optimal and Low-Switching Algorithm for Reinforcement Learning with General Function Approximation
par: Zhao, Heyang, et autres
Publié: (2023)

SLowcal-SGD: Slow Query Points Improve Local-SGD for Stochastic Convex Optimization
par: Dahan, Tehila, et autres
Publié: (2023)

Making SGD Parameter-Free
par: Carmon, Yair, et autres
Publié: (2022)

On the Trajectories of SGD Without Replacement
par: Beneventano, Pierfrancesco
Publié: (2023)