Copertina

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

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Matveev, Maria, Fojtik, Vit, Chou, Hung-Hsu, Kutyniok, Gitta, Maly, Johannes
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Computability of Classification and Deep Learning: From Theoretical Limits to Practical Feasibility through Quantization
di: Boche, Holger, et al.
Pubblicazione: (2024)

A General Constructive Upper Bound on Shallow Neural Nets Complexity
di: Hakl, Frantisek, et al.
Pubblicazione: (2025)

GradPCA: Leveraging NTK Alignment for Reliable Out-of-Distribution Detection
di: Seleznova, Mariia, et al.
Pubblicazione: (2025)

More is Less: Inducing Sparsity via Overparameterization
di: Chou, Hung-Hsu, et al.
Pubblicazione: (2021)

Implicit Regularization in Perturbed Deep Matrix Factorization: Spectral Conditions and Stability
di: Wang, Jingzhe, et al.
Pubblicazione: (2026)

Probabilistic neural operators for functional uncertainty quantification
di: Bülte, Christopher, et al.
Pubblicazione: (2025)

Random Spiking Neural Networks are Stable and Spectrally Simple
di: Araya, Ernesto, et al.
Pubblicazione: (2025)

Generalization Bounds for Message Passing Networks on Mixture of Graphons
di: Maskey, Sohir, et al.
Pubblicazione: (2024)

Adaptive-CaRe: Adaptive Causal Regularization for Robust Outcome Prediction
di: Bhasker, Nithya, et al.
Pubblicazione: (2026)

Robust identifiability for symbolic recovery of differential equations
di: Hauger, Hillary, et al.
Pubblicazione: (2024)

Mathematical Algorithm Design for Deep Learning under Societal and Judicial Constraints: The Algorithmic Transparency Requirement
di: Boche, Holger, et al.
Pubblicazione: (2024)

Graph Representational Learning: When Does More Expressivity Hurt Generalization?
di: Maskey, Sohir, et al.
Pubblicazione: (2025)

Improved probabilistic regression using diffusion models
di: Kneissl, Carlo, et al.
Pubblicazione: (2025)

Uncertainty Quantification for Regression: A Unified Framework based on kernel scores
di: Bülte, Christopher, et al.
Pubblicazione: (2025)

Weisfeiler and Leman Go Loopy: A New Hierarchy for Graph Representational Learning
di: Paolino, Raffaele, et al.
Pubblicazione: (2024)

ParFam -- (Neural Guided) Symbolic Regression Based on Continuous Global Optimization
di: Scholl, Philipp, et al.
Pubblicazione: (2023)

Symbolic Recovery of Differential Equations: The Identifiability Problem
di: Scholl, Philipp, et al.
Pubblicazione: (2022)

Robust Implicit Regularization via Weight Normalization
di: Chou, Hung-Hsu, et al.
Pubblicazione: (2023)

Dataset of Pathloss and ToA Radio Maps With Localization Application
di: Yapar, Çağkan, et al.
Pubblicazione: (2022)

Time to Spike? Understanding the Representational Power of Spiking Neural Networks in Discrete Time
di: Nguyen, Duc Anh, et al.
Pubblicazione: (2025)

Graph Neural Networks for Enhancing Ensemble Forecasts of Extreme Rainfall
di: Bülte, Christopher, et al.
Pubblicazione: (2025)

Revisiting Glorot Initialization for Long-Range Linear Recurrences
di: Bar, Noga, et al.
Pubblicazione: (2025)

An Axiomatic Assessment of Entropy- and Variance-based Uncertainty Quantification in Regression
di: Bülte, Christopher, et al.
Pubblicazione: (2025)

Sharpness-Aware Minimization and the Edge of Stability
di: Long, Philip M., et al.
Pubblicazione: (2023)

Sparse-Aware Neural Networks for Nonlinear Functionals: Mitigating the Exponential Dependence on Dimension
di: Li, Jianfei, et al.
Pubblicazione: (2026)

Understanding Multimodal Failure in Action-Chunking Behavioral Cloning
di: Mazza, Lorenzo, et al.
Pubblicazione: (2026)

The Price of Robustness: Stable Classifiers Need Overparameterization
di: von Berg, Jonas, et al.
Pubblicazione: (2026)

Recovering Simultaneously Structured Data via Non-Convex Iteratively Reweighted Least Squares
di: Kümmerle, Christian, et al.
Pubblicazione: (2023)

How to induce regularization in linear models: A guide to reparametrizing gradient flow
di: Chou, Hung-Hsu, et al.
Pubblicazione: (2023)

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

Interpretable Robotic Friction Learning via Symbolic Regression
di: Scholl, Philipp, et al.
Pubblicazione: (2025)

Momentum Further Constrains Sharpness at the Edge of Stochastic Stability
di: Andreyev, Arseniy, et al.
Pubblicazione: (2026)

Nuclear Norm Regularization for Deep Learning
di: Scarvelis, Christopher, et al.
Pubblicazione: (2024)

Sharpness-Aware Minimization Revisited: Weighted Sharpness as a Regularization Term
di: Yue, Yun, et al.
Pubblicazione: (2023)

Learning-based adaption of robotic friction models
di: Scholl, Philipp, et al.
Pubblicazione: (2023)

When is a System Discoverable from Data? Discovery Requires Chaos
di: Shumaylov, Zakhar, et al.
Pubblicazione: (2025)

A Regularization-Sharpness Tradeoff for Linear Interpolators
di: Hu, Qingyi, et al.
Pubblicazione: (2026)

Adaptive Norm-Based Regularization for Neural Networks
di: Qasim, Muhammad, et al.
Pubblicazione: (2026)

FlowTouch: View-Invariant Visuo-Tactile Prediction
di: Bien, Seongjin, et al.
Pubblicazione: (2026)

Sharp Analysis for KL-Regularized Contextual Bandits and RLHF
di: Zhao, Heyang, et al.
Pubblicazione: (2024)