Image de couverture de livre

Conflicting Biases at the Edge of Stability: Norm versus Sharpness Regularization

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Matveev, Maria, Fojtik, Vit, Chou, Hung-Hsu, Kutyniok, Gitta, Maly, Johannes
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Computability of Classification and Deep Learning: From Theoretical Limits to Practical Feasibility through Quantization
par: Boche, Holger, et autres
Publié: (2024)

A General Constructive Upper Bound on Shallow Neural Nets Complexity
par: Hakl, Frantisek, et autres
Publié: (2025)

GradPCA: Leveraging NTK Alignment for Reliable Out-of-Distribution Detection
par: Seleznova, Mariia, et autres
Publié: (2025)

More is Less: Inducing Sparsity via Overparameterization
par: Chou, Hung-Hsu, et autres
Publié: (2021)

Implicit Regularization in Perturbed Deep Matrix Factorization: Spectral Conditions and Stability
par: Wang, Jingzhe, et autres
Publié: (2026)

Probabilistic neural operators for functional uncertainty quantification
par: Bülte, Christopher, et autres
Publié: (2025)

Random Spiking Neural Networks are Stable and Spectrally Simple
par: Araya, Ernesto, et autres
Publié: (2025)

Generalization Bounds for Message Passing Networks on Mixture of Graphons
par: Maskey, Sohir, et autres
Publié: (2024)

Adaptive-CaRe: Adaptive Causal Regularization for Robust Outcome Prediction
par: Bhasker, Nithya, et autres
Publié: (2026)

Robust identifiability for symbolic recovery of differential equations
par: Hauger, Hillary, et autres
Publié: (2024)

Mathematical Algorithm Design for Deep Learning under Societal and Judicial Constraints: The Algorithmic Transparency Requirement
par: Boche, Holger, et autres
Publié: (2024)

Graph Representational Learning: When Does More Expressivity Hurt Generalization?
par: Maskey, Sohir, et autres
Publié: (2025)

Improved probabilistic regression using diffusion models
par: Kneissl, Carlo, et autres
Publié: (2025)

Uncertainty Quantification for Regression: A Unified Framework based on kernel scores
par: Bülte, Christopher, et autres
Publié: (2025)

Weisfeiler and Leman Go Loopy: A New Hierarchy for Graph Representational Learning
par: Paolino, Raffaele, et autres
Publié: (2024)

ParFam -- (Neural Guided) Symbolic Regression Based on Continuous Global Optimization
par: Scholl, Philipp, et autres
Publié: (2023)

Symbolic Recovery of Differential Equations: The Identifiability Problem
par: Scholl, Philipp, et autres
Publié: (2022)

Robust Implicit Regularization via Weight Normalization
par: Chou, Hung-Hsu, et autres
Publié: (2023)

Dataset of Pathloss and ToA Radio Maps With Localization Application
par: Yapar, Çağkan, et autres
Publié: (2022)

Time to Spike? Understanding the Representational Power of Spiking Neural Networks in Discrete Time
par: Nguyen, Duc Anh, et autres
Publié: (2025)

Graph Neural Networks for Enhancing Ensemble Forecasts of Extreme Rainfall
par: Bülte, Christopher, et autres
Publié: (2025)

Revisiting Glorot Initialization for Long-Range Linear Recurrences
par: Bar, Noga, et autres
Publié: (2025)

An Axiomatic Assessment of Entropy- and Variance-based Uncertainty Quantification in Regression
par: Bülte, Christopher, et autres
Publié: (2025)

Sharpness-Aware Minimization and the Edge of Stability
par: Long, Philip M., et autres
Publié: (2023)

Sparse-Aware Neural Networks for Nonlinear Functionals: Mitigating the Exponential Dependence on Dimension
par: Li, Jianfei, et autres
Publié: (2026)

Understanding Multimodal Failure in Action-Chunking Behavioral Cloning
par: Mazza, Lorenzo, et autres
Publié: (2026)

The Price of Robustness: Stable Classifiers Need Overparameterization
par: von Berg, Jonas, et autres
Publié: (2026)

Recovering Simultaneously Structured Data via Non-Convex Iteratively Reweighted Least Squares
par: Kümmerle, Christian, et autres
Publié: (2023)

How to induce regularization in linear models: A guide to reparametrizing gradient flow
par: Chou, Hung-Hsu, et autres
Publié: (2023)

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

Interpretable Robotic Friction Learning via Symbolic Regression
par: Scholl, Philipp, et autres
Publié: (2025)

Momentum Further Constrains Sharpness at the Edge of Stochastic Stability
par: Andreyev, Arseniy, et autres
Publié: (2026)

Nuclear Norm Regularization for Deep Learning
par: Scarvelis, Christopher, et autres
Publié: (2024)

Sharpness-Aware Minimization Revisited: Weighted Sharpness as a Regularization Term
par: Yue, Yun, et autres
Publié: (2023)

Learning-based adaption of robotic friction models
par: Scholl, Philipp, et autres
Publié: (2023)

When is a System Discoverable from Data? Discovery Requires Chaos
par: Shumaylov, Zakhar, et autres
Publié: (2025)

A Regularization-Sharpness Tradeoff for Linear Interpolators
par: Hu, Qingyi, et autres
Publié: (2026)

Adaptive Norm-Based Regularization for Neural Networks
par: Qasim, Muhammad, et autres
Publié: (2026)

FlowTouch: View-Invariant Visuo-Tactile Prediction
par: Bien, Seongjin, et autres
Publié: (2026)

Sharp Analysis for KL-Regularized Contextual Bandits and RLHF
par: Zhao, Heyang, et autres
Publié: (2024)