Cover Image

Deep Exploration of Epoch-wise Double Descent in Noisy Data: Signal Separation, Large Activation, and Benign Overfitting

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kubo, Tomoki, Uda, Ryuken, Iida, Yusuke
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Benign, Tempered, or Catastrophic: A Taxonomy of Overfitting
by: Mallinar, Neil, et al.
Published: (2022)

Unveil Benign Overfitting for Transformer in Vision: Training Dynamics, Convergence, and Generalization
by: Jiang, Jiarui, et al.
Published: (2024)

Understanding the Double Descent Phenomenon in Deep Learning
by: Lafon, Marc, et al.
Published: (2024)

Application of Deep Learning Methods to Processing of Noisy Medical Video Data
by: Afonchikov, Danil, et al.
Published: (2024)

Atomic Depth Estimation From Noisy Electron Microscopy Data Via Deep Learning
by: Leibovich, Matan, et al.
Published: (2026)

Activation-wise Propagation: A One-Timestep Strategy for Spiking Neural Networks
by: Song, Jian, et al.
Published: (2025)

On the Relationship Between Double Descent of CNNs and Shape/Texture Bias Under Learning Process
by: Iwase, Shun, et al.
Published: (2025)

Epoch-evolving Gaussian Process Guided Learning
by: Cui, Jiabao, et al.
Published: (2020)

Conformal-in-the-Loop for Learning with Imbalanced Noisy Data
by: Graham-Knight, John Brandon, et al.
Published: (2024)

Inverse-Free Fast Natural Gradient Descent Method for Deep Learning
by: Ou, Xinwei, et al.
Published: (2024)

Class-wise Balancing Data Replay for Federated Class-Incremental Learning
by: Qi, Zhuang, et al.
Published: (2025)

Data Overfitting for On-Device Super-Resolution with Dynamic Algorithm and Compiler Co-Design
by: Li, Gen, et al.
Published: (2024)

Perturbing the Gradient for Alleviating Meta Overfitting
by: Gogoi, Manas, et al.
Published: (2024)

Noise-Tolerant Hybrid Prototypical Learning with Noisy Web Data
by: Liang, Chao, et al.
Published: (2025)

Preventing Catastrophic Overfitting in Fast Adversarial Training: A Bi-level Optimization Perspective
by: Wang, Zhaoxin, et al.
Published: (2024)

Adversarially Diversified Rehearsal Memory (ADRM): Mitigating Memory Overfitting Challenge in Continual Learning
by: Khan, Hikmat, et al.
Published: (2024)

DQA: An Efficient Method for Deep Quantization of Deep Neural Network Activations
by: Hu, Wenhao, et al.
Published: (2024)

FUN-AD: Fully Unsupervised Learning for Anomaly Detection with Noisy Training Data
by: Im, Jiin, et al.
Published: (2024)

Estimating Noisy Class Posterior with Part-level Labels for Noisy Label Learning
by: Zhao, Rui, et al.
Published: (2024)

Towards Class-wise Robustness Analysis
by: Medi, Tejaswini, et al.
Published: (2024)

Explaining Model Overfitting in CNNs via GMM Clustering
by: Dou, Hui, et al.
Published: (2024)

ChannelExplorer: Exploring Class Separability Through Activation Channel Visualization
by: Zaman, Md Rahat-uz-, et al.
Published: (2025)

Coordinate Descent for Network Linearization
by: Rakhlin, Vlad, et al.
Published: (2025)

Dual-granularity Sinkhorn Distillation for Enhanced Learning from Long-tailed Noisy Data
by: Hong, Feng, et al.
Published: (2025)

Exploring Time Conditioning in Diffusion Generative Models from Disjoint Noisy Data Manifolds
by: Li, Liuzhuozheng, et al.
Published: (2026)

Noisy Annotations in Semantic Segmentation
by: Kimhi, Moshe, et al.
Published: (2024)

Learning to Transform for Generalizable Instance-wise Invariance
by: Singhal, Utkarsh, et al.
Published: (2023)

Learning with Open-world Noisy Data via Class-independent Margin in Dual Representation Space
by: Pan, Linchao, et al.
Published: (2025)

Models as Lego Builders: Assembling Malice from Benign Blocks via Semantic Blueprints
by: Li, Chenxi, et al.
Published: (2026)

Activation Map Compression through Tensor Decomposition for Deep Learning
by: Nguyen, Le-Trung, et al.
Published: (2024)

Active Learning with a Noisy Annotator
by: Shafir, Netta, et al.
Published: (2025)

Instance-wise Supervision-level Optimization in Active Learning
by: Matsuo, Shinnosuke, et al.
Published: (2025)

Deep Clustering Using the Soft Silhouette Score: Towards Compact and Well-Separated Clusters
by: Vardakas, Georgios, et al.
Published: (2024)

Benign Overfitting without Linearity: Neural Network Classifiers Trained by Gradient Descent for Noisy Linear Data
by: Frei, Spencer, et al.
Published: (2022)

ReLaX: Reasoning with Latent Exploration for Large Reasoning Models
by: Zhang, Shimin, et al.
Published: (2025)

High-Resolution Image Reconstruction with Unsupervised Learning and Noisy Data Applied to Ion-Beam Dynamics for Particle Accelerators
by: Osswald, Francis, et al.
Published: (2026)

SoftPatch: Unsupervised Anomaly Detection with Noisy Data
by: Jiang, Xi, et al.
Published: (2024)

Progressive Element-wise Gradient Estimation for Neural Network Quantization
by: Zhao, Kaiqi
Published: (2025)

Federated Learning with Instance-Dependent Noisy Label
by: Wang, Lei, et al.
Published: (2023)

Joint Asymmetric Loss for Learning with Noisy Labels
by: Wang, Jialiang, et al.
Published: (2025)