Image de couverture de livre

Spectral Signatures of Data Quality: Eigenvalue Tail Index as a Diagnostic for Label Noise in Neural Networks

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Loftus, Matthew
Format:	Preprint
Publié:	2026
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

The Malignant Tail: Spectral Segregation of Label Noise in Over-Parameterized Networks
par: Wang, Zice
Publié: (2026)

The topological gap at criticality: scaling exponent d + η, universality, and scope
par: Loftus, Matthew
Publié: (2026)

Improving Expressive Power of Spectral Graph Neural Networks with Eigenvalue Correction
par: Lu, Kangkang, et autres
Publié: (2024)

Persistence diagrams of random matrices via Morse theory: universality and a new spectral diagnostic
par: Loftus, Matthew
Publié: (2026)

Scale-Invariant Neural Network Optimization: Norm Geometry and Heavy-Tailed Noise
par: Zhang, Jiayu, et autres
Publié: (2026)

Spectral Reach: Understanding Neural Scaling as Progress into the Spectral Tail
par: Nikolaou, Konstantin, et autres
Publié: (2026)

How much of persistent homology is topology? A quantitative decomposition for spin model phase transitions
par: Loftus, Matthew
Publié: (2026)

From Spikes to Heavy Tails: Unveiling the Spectral Evolution of Neural Networks
par: Kothapalli, Vignesh, et autres
Publié: (2024)

Graph Neural Networks with Coarse- and Fine-Grained Division for Mitigating Label Sparsity and Noise
par: Li, Shuangjie, et autres
Publié: (2024)

Mitigating Label Noise through Data Ambiguation
par: Lienen, Julian, et autres
Publié: (2023)

Generating the Ground Truth: Synthetic Data for Soft Label and Label Noise Research
par: de Vries, Sjoerd, et autres
Publié: (2023)

STNet: Spectral Transformation Network for Solving Operator Eigenvalue Problem
par: Wang, Hong, et autres
Publié: (2025)

Capsule Neural Networks as Noise Stabilizer for Time Series Data
par: Kim, Soyeon, et autres
Publié: (2024)

Decentralized Neural Networks for Robust and Scalable Eigenvalue Computation
par: Katende, Ronald
Publié: (2024)

Learning from Reduced Labels for Long-Tailed Data
par: Wei, Meng, et autres
Publié: (2024)

Stochastic Bilevel Optimization with Heavy-Tailed Noise
par: Liu, Zhuanghua, et autres
Publié: (2025)

High-Dimensional Tail Index Regression
par: Sasaki, Yuya, et autres
Publié: (2024)

Fair Differentiable Neural Network Architecture Search for Long-Tailed Data with Self-Supervised Learning
par: Yan, Jiaming
Publié: (2024)

Clustering with Neural Network and Index
par: Liu, Gangli
Publié: (2022)

Early Stopping Against Label Noise Without Validation Data
par: Yuan, Suqin, et autres
Publié: (2025)

Stability and Generalization of Nonconvex Optimization with Heavy-Tailed Noise
par: Chen, Hongxu, et autres
Publié: (2026)

Efficient Distributed Optimization under Heavy-Tailed Noise
par: Lee, Su Hyeong, et autres
Publié: (2025)

NoisyGL: A Comprehensive Benchmark for Graph Neural Networks under Label Noise
par: Wang, Zhonghao, et autres
Publié: (2024)

How Label Imbalance Shapes Geometry: A General Spectral Analysis of Multi-Label Neural Collapse
par: Ma, Xiaoxuan, et autres
Publié: (2026)

Learning to Hear Broken Motors: Signature-Guided Data Augmentation for Induction-Motor Diagnostics
par: Ali, Saraa, et autres
Publié: (2025)

Learning from Imperfect Text Guidance: Robust Long-Tail Visual Recognition with High-Noise Label
par: Li, Mengke, et autres
Publié: (2026)

Label Noise: Ignorance Is Bliss
par: Zhu, Yilun, et autres
Publié: (2024)

Temporal Motif Signatures for Temporal Graph Neural Networks
par: Sandfelder, Dylan, et autres
Publié: (2026)

Can SGD Handle Heavy-Tailed Noise?
par: Fatkhullin, Ilyas, et autres
Publié: (2025)

Federated Stochastic Minimax Optimization under Heavy-Tailed Noises
par: Zhang, Xinwen, et autres
Publié: (2025)

On the Eigenvalue Decay Rates of a Class of Neural-Network Related Kernel Functions Defined on General Domains
par: Li, Yicheng, et autres
Publié: (2023)

SpectralNet: Spectral Clustering using Deep Neural Networks
par: Shaham, Uri, et autres
Publié: (2018)

Spectral Pruning for Recurrent Neural Networks
par: Furuya, Takashi, et autres
Publié: (2021)

Label-Noise Robust Diffusion Models
par: Na, Byeonghu, et autres
Publié: (2024)

Label Noise: Correcting the Forward-Correction
par: Toner, William, et autres
Publié: (2023)

Regretful Decisions under Label Noise
par: Nagaraj, Sujay, et autres
Publié: (2025)

Why is SAM Robust to Label Noise?
par: Baek, Christina, et autres
Publié: (2024)

Understanding Robust Machine Learning for Nonparametric Regression with Heavy-Tailed Noise
par: Feng, Yunlong, et autres
Publié: (2025)

The Effect of Label Noise on the Information Content of Neural Representations
par: Umar, Ali Hussaini, et autres
Publié: (2025)

A Robust Monotonic Single-Index Model for Skewed and Heavy-Tailed Data: A Deep Neural Network Approach Applied to Periodontal Studies
par: Liu, Qingyang, et autres
Publié: (2025)