Cover Image

Rod Flow: A Continuous-Time Model for Gradient Descent at the Edge of Stability

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Regis, Eric, Chewi, Sinho
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence Optimization and Control
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

A Rod Flow Model for Adam at the Edge of Stability
by: Regis, Eric, et al.
Published: (2026)

Finite-Time Analysis of Gradient Descent for Shallow Transformers
by: Arda, Enes, et al.
Published: (2026)

Gradient Descent Efficiency Index
by: Dhingra, Aviral
Published: (2024)

Lectures on optimization
by: Chewi, Sinho
Published: (2026)

Almost Bayesian: The Fractal Dynamics of Stochastic Gradient Descent
by: Hennick, Max, et al.
Published: (2025)

On the Convergence of (Stochastic) Gradient Descent for Kolmogorov--Arnold Networks
by: Gao, Yihang, et al.
Published: (2024)

Algorithms for mean-field variational inference via polyhedral optimization in the Wasserstein space
by: Jiang, Yiheng, et al.
Published: (2023)

Weighted Low-rank Approximation via Stochastic Gradient Descent on Manifolds
by: Xu, Conglong, et al.
Published: (2025)

Deterministic Policy Gradient for Reinforcement Learning with Continuous Time and State
by: Cheng, Ziheng, et al.
Published: (2025)

Enhancing Stochastic Gradient Descent: A Unified Framework and Novel Acceleration Methods for Faster Convergence
by: Deng, Yichuan, et al.
Published: (2024)

Non-Euclidean Gradient Descent Operates at the Edge of Stability
by: Islamov, Rustem, et al.
Published: (2026)

Stability of Primal-Dual Gradient Flow Dynamics for Multi-Block Convex Optimization Problems
by: Ozaslan, Ibrahim K., et al.
Published: (2024)

SGD at the Edge of Stability: The Stochastic Sharpness Gap
by: Liao, Fangshuo, et al.
Published: (2026)

Convergence Rates for Gradient Descent on the Edge of Stability in Overparametrised Least Squares
by: MacDonald, Lachlan Ewen, et al.
Published: (2025)

Boosting Gradient Ascent for Continuous DR-submodular Maximization
by: Zhang, Qixin, et al.
Published: (2024)

Implicit Regularization of Gradient Flow on One-Layer Softmax Attention
by: Sheen, Heejune, et al.
Published: (2024)

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

Jacobian Descent for Multi-Objective Optimization
by: Quinton, Pierre, et al.
Published: (2024)

Policy Optimization in Hybrid Discrete-Continuous Action Spaces via Mixed Gradients
by: Alvo, Matias, et al.
Published: (2026)

A Single-Loop Gradient Descent and Perturbed Ascent Algorithm for Nonconvex Functional Constrained Optimization
by: Lu, Songtao
Published: (2022)

Decoupled Continuous-Time Reinforcement Learning via Hamiltonian Flow
by: Nguyen, Minh
Published: (2026)

Multi-head Transformers Provably Learn Symbolic Multi-step Reasoning via Gradient Descent
by: Yang, Tong, et al.
Published: (2025)

Controlling the Flow: Stability and Convergence for Stochastic Gradient Descent with Decaying Regularization
by: Kassing, Sebastian, et al.
Published: (2025)

Kinematic Tokenization: Optimization-Based Continuous-Time Tokens for Learnable Decision Policies in Noisy Time Series
by: Kearney, Griffin
Published: (2026)

Delightful Policy Gradient
by: Osband, Ian
Published: (2026)

Isotropic Curvature Model for Understanding Deep Learning Optimization: Is Gradient Orthogonalization Optimal?
by: Su, Weijie
Published: (2025)

Explicit and data-Efficient Encoding via Gradient Flow
by: Flouris, Kyriakos, et al.
Published: (2024)

Delightful Distributed Policy Gradient
by: Osband, Ian
Published: (2026)

Robust Control with Gradient Uncertainty
by: Qi, Qian
Published: (2025)

A Retention-Centric Framework for Continual Learning with Guaranteed Model Developmental Safety
by: Li, Gang, et al.
Published: (2024)

A Unified Framework for Gradient Aggregation in Multi-Objective Optimization
by: Hu, Zeou, et al.
Published: (2026)

Asynchronous Distributed Reinforcement Learning for LQR Control via Zeroth-Order Block Coordinate Descent
by: Jing, Gangshan, et al.
Published: (2021)

Unbiased Gradient Low-Rank Projection
by: Pan, Rui, et al.
Published: (2025)

Sublinear Regret for a Class of Continuous-Time Linear-Quadratic Reinforcement Learning Problems
by: Huang, Yilie, et al.
Published: (2024)

Riemann Sum Optimization for Accurate Integrated Gradients Computation
by: Swain, Swadesh, et al.
Published: (2024)

Performative Policy Gradient: Optimality in Performative Reinforcement Learning
by: Basu, Debabrota, et al.
Published: (2025)

A Methodology Establishing Linear Convergence of Adaptive Gradient Methods under PL Inequality
by: Chakrabarti, Kushal, et al.
Published: (2024)

Data-Driven Exploration for a Class of Continuous-Time Indefinite Linear--Quadratic Reinforcement Learning Problems
by: Huang, Yilie, et al.
Published: (2025)

Sven: Singular Value Descent as a Computationally Efficient Natural Gradient Method
by: Bright-Thonney, Samuel, et al.
Published: (2026)

On the Optimal Construction of Unbiased Gradient Estimators for Zeroth-Order Optimization
by: Ma, Shaocong, et al.
Published: (2025)