Image de couverture de livre

Grokking at the Edge of Numerical Stability

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Prieto, Lucas, Barsbey, Melih, Mediano, Pedro A. M., Birdal, Tolga
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

From Data Statistics to Feature Geometry: How Correlations Shape Superposition
par: Prieto, Lucas, et autres
Publié: (2026)

Large Learning Rates Simultaneously Achieve Robustness to Spurious Correlations and Compressibility
par: Barsbey, Melih, et autres
Publié: (2025)

Adversarial Attacks Leverage Interference Between Features in Superposition
par: Stevinson, Edward, et autres
Publié: (2025)

On the Interaction of Compressibility and Adversarial Robustness
par: Barsbey, Melih, et autres
Publié: (2025)

Generalization at the Edge of Stability
par: Tuci, Mario, et autres
Publié: (2026)

Probabilistic Sampling of Balanced K-Means using Adiabatic Quantum Computing
par: Zaech, Jan-Nico, et autres
Publié: (2023)

CuMPerLay: Learning Cubical Multiparameter Persistence Vectorizations
par: Korkmaz, Caner, et autres
Publié: (2025)

Parallelised Differentiable Straightest Geodesics for 3D Meshes
par: Verninas, Hippolyte, et autres
Publié: (2026)

Variational Inference for Lévy Process-Driven SDEs via Neural Tilting
par: Kindap, Yaman, et autres
Publié: (2026)

Fractional Diffusion Bridge Models
par: Nobis, Gabriel, et autres
Publié: (2025)

UV-free Texture Generation with Denoising and Geodesic Heat Diffusions
par: Foti, Simone, et autres
Publié: (2024)

Attending to Topological Spaces: The Cellular Transformer
par: Ballester, Rubén, et autres
Publié: (2024)

Continuous-Time SO(3) Forecasting with Savitzky--Golay Neural Controlled Differential Equations
par: Bastian, Lennart, et autres
Publié: (2025)

Bayesian Conditioned Diffusion Models for Inverse Problems
par: Güngör, Alper, et autres
Publié: (2024)

AdvSecureNet: A Python Toolkit for Adversarial Machine Learning
par: Catal, Melih, et autres
Publié: (2024)

Scaling-Aware Data Selection for End-to-End Autonomous Driving Systems
par: Dimlioglu, Tolga, et autres
Publié: (2026)

Extrapolation of Periodic Functions Using Binary Encoding of Continuous Numerical Values
par: Powell, Brian P., et autres
Publié: (2025)

PRISM: Distributed Inference for Foundation Models at Edge
par: Qazi, Muhammad Azlan, et autres
Publié: (2025)

EdgeFusion: On-Device Text-to-Image Generation
par: Castells, Thibault, et autres
Publié: (2024)

Enhancing Convolutional Neural Networks with Higher-Order Numerical Difference Methods
par: Wang, Qi, et autres
Publié: (2024)

Early Exiting Predictive Coding Neural Networks for Edge AI
par: Zniber, Alaa, et autres
Publié: (2023)

PaSTe: Improving the Efficiency of Visual Anomaly Detection at the Edge
par: Barusco, Manuel, et autres
Publié: (2024)

Edge AI: Evaluation of Model Compression Techniques for Convolutional Neural Networks
par: Francy, Samer, et autres
Publié: (2024)

Fun with Flags: Robust Principal Directions via Flag Manifolds
par: Mankovich, Nathan, et autres
Publié: (2024)

EDNet: Edge-Optimized Small Target Detection in UAV Imagery -- Faster Context Attention, Better Feature Fusion, and Hardware Acceleration
par: Song, Zhifan, et autres
Publié: (2025)

Edge-case Synthesis for Fisheye Object Detection: A Data-centric Perspective
par: Kim, Seunghyeon, et autres
Publié: (2025)

On-Demand Multi-Task Sparsity for Efficient Large-Model Deployment on Edge Devices
par: Huang, Lianming, et autres
Publié: (2025)

Developing a Resource-Constraint EdgeAI model for Surface Defect Detection
par: Mih, Atah Nuh, et autres
Publié: (2023)

LightCL: Compact Continual Learning with Low Memory Footprint For Edge Device
par: Wang, Zeqing, et autres
Publié: (2024)

SADA: Stability-guided Adaptive Diffusion Acceleration
par: Jiang, Ting, et autres
Publié: (2025)

Secure and Storage-Efficient Deep Learning Models for Edge AI Using Automatic Weight Generation
par: Rahaman, Habibur, et autres
Publié: (2025)

Semantic Communication based on Generative AI: A New Approach to Image Compression and Edge Optimization
par: Pezone, Francesco
Publié: (2025)

Bridging the Rural Healthcare Gap: A Cascaded Edge-Cloud Architecture for Automated Retinal Screening
par: Doshi, Nishi, et autres
Publié: (2026)

Achieving Pareto Optimality using Efficient Parameter Reduction for DNNs in Resource-Constrained Edge Environment
par: Mih, Atah Nuh, et autres
Publié: (2024)

An approach based on class activation maps for investigating the effects of data augmentation on neural networks for image classification
par: Dorneles, Lucas M., et autres
Publié: (2025)

STAR: Stability-Inducing Weight Perturbation for Continual Learning
par: Eskandar, Masih, et autres
Publié: (2025)

EdgeMLOps: Operationalizing ML models with Cumulocity IoT and thin-edge.io for Visual quality Inspection
par: Chaturvedi, Kanishk, et autres
Publié: (2025)

Edge-preserving noise for diffusion models
par: Vandersanden, Jente, et autres
Publié: (2024)

Evaluating the Stability of Semantic Concept Representations in CNNs for Robust Explainability
par: Mikriukov, Georgii, et autres
Publié: (2023)

Exploring the Stability Gap in Continual Learning: The Role of the Classification Head
par: Łapacz, Wojciech, et autres
Publié: (2024)