Cover Image

Momentum Further Constrains Sharpness at the Edge of Stochastic Stability

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Andreyev, Arseniy, Ananthkumar, Advikar, Walden, Marc, Poggio, Tomaso, Beneventano, Pierfrancesco
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Dynamical Systems Optimization and Control
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Edge of Stochastic Stability: Revisiting the Edge of Stability for SGD
by: Andreyev, Arseniy, et al.
Published: (2024)

Too Sharp, Too Sure: When Calibration Follows Curvature
by: Morosini, Alessandro, et al.
Published: (2026)

How Neural Networks Learn the Support is an Implicit Regularization Effect of SGD
by: Beneventano, Pierfrancesco, et al.
Published: (2024)

Does Weight Decay Enhance Training Stability?
by: Saether, Marius, et al.
Published: (2026)

Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias
by: Das, Mohua, et al.
Published: (2026)

On the Trajectories of SGD Without Replacement
by: Beneventano, Pierfrancesco
Published: (2023)

Zeroth-Order Optimization at the Edge of Stability
by: Song, Minhak, et al.
Published: (2026)

Does SGD Seek Flatness or Sharpness? An Exactly Solvable Model
by: Xu, Yizhou, et al.
Published: (2026)

Gradient Descent Converges Linearly to Flatter Minima than Gradient Flow in Shallow Linear Networks
by: Beneventano, Pierfrancesco, et al.
Published: (2025)

pAI/MSc: ML Theory Research with Humans on the Loop
by: Abdelmoneum, Mahmoud, et al.
Published: (2026)

Stability properties of gradient flow dynamics for the symmetric low-rank matrix factorization problem
by: Mohammadi, Hesameddin, et al.
Published: (2024)

Stability-Certified Learning of Control Systems with Quadratic Nonlinearities
by: Duff, Igor Pontes, et al.
Published: (2024)

Regularity and Stability Properties of Selective SSMs with Discontinuous Gating
by: Zubić, Nikola, et al.
Published: (2025)

Safe and Robust Domains of Attraction for Discrete-Time Systems: A Set-Based Characterization and Certifiable Neural Network Estimation
by: Serry, Mohamed, et al.
Published: (2026)

SINDy-RL: Interpretable and Efficient Model-Based Reinforcement Learning
by: Zolman, Nicholas, et al.
Published: (2024)

Data-driven Nonlinear Model Reduction using Koopman Theory: Integrated Control Form and NMPC Case Study
by: Schulze, Jan C., et al.
Published: (2024)

Near-Optimal Distributed Linear-Quadratic Regulator for Networked Systems
by: Shin, Sungho, et al.
Published: (2022)

Learning Dissipative Neural Dynamical Systems
by: Xu, Yuezhu, et al.
Published: (2023)

Tradeoffs between convergence rate and noise amplification for momentum-based accelerated optimization algorithms
by: Mohammadi, Hesameddin, et al.
Published: (2022)

Observability conditions for neural state-space models with eigenvalues and their roots of unity
by: Gracyk, Andrew
Published: (2025)

Safely Learning Dynamical Systems
by: Ahmadi, Amir Ali, et al.
Published: (2023)

From exponential to finite/fixed-time stability: Applications to optimization
by: Ozaslan, Ibrahim K., et al.
Published: (2024)

Neural Operators for Predictor Feedback Control of Nonlinear Delay Systems
by: Bhan, Luke, et al.
Published: (2024)

Identifiability of Differential-Algebraic Systems
by: Montanari, Arthur N., et al.
Published: (2024)

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

The Global Empirical NTK: Self-Referential Bias and Dimensionality of Gradient Descent Learning
by: Hazelden, James, et al.
Published: (2026)

Convergence of optimizers implies eigenvalues filtering at equilibrium
by: Bolte, Jerome, et al.
Published: (2025)

Circular Microalgae-Based Carbon Control for Net Zero
by: Zocco, Federico, et al.
Published: (2025)

Near-optimal Closed-loop Method via Lyapunov Damping for Convex Optimization
by: Maier, Severin, et al.
Published: (2023)

Nonlinear Dynamics In Optimization Landscape of Shallow Neural Networks with Tunable Leaky ReLU
by: Liu, Jingzhou
Published: (2025)

Synchronization on circles and spheres with nonlinear interactions
by: Criscitiello, Christopher, et al.
Published: (2024)

On the Convergence of Overlapping Schwarz Decomposition for Nonlinear Optimal Control
by: Na, Sen, et al.
Published: (2020)

Learning Spatio-Temporal Dynamics via Operator-Valued RKHS and Kernel Koopman Methods
by: Withanachchi, Mahishanka
Published: (2025)

Memorization and Regularization in Generative Diffusion Models
by: Baptista, Ricardo, et al.
Published: (2025)

Kernel Sum of Squares for Data Adapted Kernel Learning of Dynamical Systems from Data: A global optimization approach
by: Lengyel, Daniel, et al.
Published: (2024)

Iterative regularization in classification via hinge loss diagonal descent
by: Apidopoulos, Vassilis, et al.
Published: (2022)

Online Optimization and Ambiguity-based Learning of Distributionally Uncertain Dynamic Systems
by: Li, Dan, et al.
Published: (2021)

Safe and Near-Optimal Control with Online Dynamics Learning
by: Prajapat, Manish, et al.
Published: (2025)

Reservoir Predictive Path Integral Control for Unknown Nonlinear Dynamics
by: Inoue, Daisuke, et al.
Published: (2025)

On Convex Data-Driven Inverse Optimal Control for Nonlinear, Non-stationary and Stochastic Systems
by: Garrabe, Emiland, et al.
Published: (2023)