Imagen de Portada

The Curvature Rate λ: A Scalar Measure of Input-Space Sharpness in Neural Networks

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Poschl, Jacob
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Active Inference with Reusable State-Dependent Value Profiles
por: Poschl, Jacob
Publicado: (2025)

LEVIS: Large Exact Verifiable Input Spaces for Neural Networks
por: Chehade, Mohamad Fares El Hajj, et al.
Publicado: (2024)

Curvature Clues: Decoding Deep Learning Privacy with Input Loss Curvature
por: Ravikumar, Deepak, et al.
Publicado: (2024)

Input Space Mode Connectivity in Deep Neural Networks
por: Vrabel, Jakub, et al.
Publicado: (2024)

Measuring Sharpness in Grokking
por: Miller, Jack, et al.
Publicado: (2024)

Neural Network Plasticity and Loss Sharpness
por: Koster, Max, et al.
Publicado: (2024)

Analyzing Neural Network Robustness Using Graph Curvature
por: Tan, Shuhang, et al.
Publicado: (2024)

Input Invex Neural Network
por: Sapkota, Suman, et al.
Publicado: (2021)

Accelerating Neural Network Training Along Sharp and Flat Directions
por: Zakarin, Daniyar, et al.
Publicado: (2025)

Sharp Convergence Rates for Masked Diffusion Models
por: Liang, Yuchen, et al.
Publicado: (2026)

Kronecker-Factored Approximate Curvature for Modern Neural Network Architectures
por: Eschenhagen, Runa, et al.
Publicado: (2023)

Unveiling Privacy, Memorization, and Input Curvature Links
por: Ravikumar, Deepak, et al.
Publicado: (2024)

A new Input Convex Neural Network with application to options pricing
por: Lemaire, Vincent, et al.
Publicado: (2024)

CR-LSO: Convex Neural Architecture Optimization in the Latent Space of Graph Variational Autoencoder with Input Convex Neural Networks
por: Rao, Xuan, et al.
Publicado: (2022)

Sharp Convergence Rates for Matching Pursuit
por: Klusowski, Jason M., et al.
Publicado: (2023)

Neural Clamping: Joint Input Perturbation and Temperature Scaling for Neural Network Calibration
por: Tang, Yung-Chen, et al.
Publicado: (2022)

Generating Realistic, Diverse, and Fault-Revealing Inputs with Latent Space Interpolation for Testing Deep Neural Networks
por: Duan, Bin, et al.
Publicado: (2025)

PERTINENCE: Input-based Opportunistic Neural Network Dynamic Execution
por: Shende, Omkar, et al.
Publicado: (2025)

Sparse-Input Neural Network using Group Concave Regularization
por: Luo, Bin, et al.
Publicado: (2023)

Stepping on the Edge: Curvature Aware Learning Rate Tuners
por: Roulet, Vincent, et al.
Publicado: (2024)

On Measuring Long-Range Interactions in Graph Neural Networks
por: Bamberger, Jacob, et al.
Publicado: (2025)

Sharp Bounds on the Approximation Rates, Metric Entropy, and $n$-widths of Shallow Neural Networks
por: Siegel, Jonathan W., et al.
Publicado: (2021)

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

Approximating Families of Sharp Solutions to Fisher's Equation with Physics-Informed Neural Networks
por: Rohrhofer, Franz M., et al.
Publicado: (2024)

Curvature Learning for Generalization of Hyperbolic Neural Networks
por: Fan, Xiaomeng, et al.
Publicado: (2025)

Compositional Curvature Bounds for Deep Neural Networks
por: Entesari, Taha, et al.
Publicado: (2024)

Sharpness Aware Surrogate Training for Spiking Neural Networks
por: Nicholson, Maximilian
Publicado: (2026)

Standard Transformers Achieve the Minimax Rate in Nonparametric Regression with $C^{s,λ}$ Targets
por: Lai, Yanming, et al.
Publicado: (2026)

Post-Training Neural Network Pruning using Graph Curvature
por: Tan, Shuhang, et al.
Publicado: (2026)

Kronecker-Factored Approximate Curvature for Physics-Informed Neural Networks
por: Dangel, Felix, et al.
Publicado: (2024)

Sharp Generalization for Nonparametric Regression in Interpolation Space by Over-Parameterized Neural Networks Trained with Preconditioned Gradient Descent and Early Stopping
por: Yang, Yingzhen, et al.
Publicado: (2024)

Benchmarking Convolutional Neural Network and Graph Neural Network based Surrogate Models on a Real-World Car External Aerodynamics Dataset
por: Jacob, Sam Jacob, et al.
Publicado: (2025)

WaterMAS: Sharpness-Aware Maximization for Neural Network Watermarking
por: Trias, Carl De Sousa, et al.
Publicado: (2024)

SO(3)-Equivariant Neural Networks for Learning from Scalar and Vector Fields on Spheres
por: Ballerin, Francesco, et al.
Publicado: (2025)

Swarm Characteristic Classification using Robust Neural Networks with Optimized Controllable Inputs
por: Peltier III, Donald W., et al.
Publicado: (2025)

Scalar Field Prediction on Meshes Using Interpolated Multi-Resolution Convolutional Neural Networks
por: Ferguson, Kevin, et al.
Publicado: (2024)

FedScalar: Federated Learning with Scalar Communication for Bandwidth-Constrained Networks
por: Rostami, M., et al.
Publicado: (2024)

Input Snapshots Fusion for Scalable Discrete-Time Dynamic Graph Neural Networks
por: Qi, QingGuo, et al.
Publicado: (2024)

Rethinking Neural Network Learning Rates: A Stackelberg Perspective
por: Zeng, Sihan, et al.
Publicado: (2026)

Sharpness-Aware Minimization: General Analysis and Improved Rates
por: Oikonomou, Dimitris, et al.
Publicado: (2025)