Cover Image

Catastrophic Overfitting, Entropy Gap and Participation Ratio: A Noiseless $l^p$ Norm Solution for Fast Adversarial Training

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Mehouachi, Fares B., Jabari, Saif Eddin
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

FlowMixer: A Depth-Agnostic Neural Architecture for Interpretable Spatiotemporal Forecasting
by: Mehouachi, Fares B., et al.
Published: (2025)

Urban traffic analysis and forecasting through shared Koopman eigenmodes
by: Yang, Chuhan, et al.
Published: (2024)

Learning Solution Operators for Partial Differential Equations via Monte Carlo-Type Approximation
by: Choutri, Salah Eddine, et al.
Published: (2025)

Unveiling the Backdoor Mechanism Hidden Behind Catastrophic Overfitting in Fast Adversarial Training
by: Zhao, Mengnan, et al.
Published: (2026)

Monte Carlo-Type Neural Operator for Differential Equations
by: Choutri, Salah Eddine, et al.
Published: (2025)

Neural operators struggle to learn complex PDEs in pedestrian mobility: Hughes model case study
by: Chauhan, Prajwal, et al.
Published: (2025)

Benign Overfitting in Adversarial Training for Vision Transformers
by: Zhang, Jiaming, et al.
Published: (2026)

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

Koopman Autoencoders Learn Neural Representation Dynamics
by: Aswani, Nishant Suresh, et al.
Published: (2025)

Risk Phase Transitions in Spiked Regression: Alignment Driven Benign and Catastrophic Overfitting
by: Li, Jiping, et al.
Published: (2025)

Exploring Sparsity and Smoothness of Arbitrary $\ell_p$ Norms in Adversarial Attacks
by: Duhme, Christof, et al.
Published: (2026)

Efficient Dilated Squeeze and Excitation Neural Operator for Differential Equations
by: Chauhan, Prajwal, et al.
Published: (2026)

Representing Neural Network Layers as Linear Operations via Koopman Operator Theory
by: Aswani, Nishant Suresh, et al.
Published: (2024)

On the Implicit Adversariality of Catastrophic Forgetting in Deep Continual Learning
by: Peng, Ze, et al.
Published: (2025)

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

Ignition Phase : Standard Training for Fast Adversarial Robustness
by: Yu-Hang, Wang, et al.
Published: (2025)

Benign Overfitting for Regression with Trained Two-Layer ReLU Networks
by: Park, Junhyung, et al.
Published: (2024)

Control of Overfitting with Physics
by: Kozyrev, Sergei V., et al.
Published: (2024)

Fast Adversarial Training against Sparse Attacks Requires Loss Smoothing
by: Zhong, Xuyang, et al.
Published: (2025)

A Coherence-Based Measure of AGI
by: Fourati, Fares
Published: (2025)

Fast-Slow Co-advancing Optimizer: Toward Harmonious Adversarial Training of GAN
by: Wang, Lin, et al.
Published: (2025)

Noiseless Privacy-Preserving Decentralized Learning
by: Biswas, Sayan, et al.
Published: (2024)

Residual Correction Models for AC Optimal Power Flow Using DC Optimal Power Flow Solutions
by: Za'ter, Muhy Eddin, et al.
Published: (2025)

Towards Mitigating Architecture Overfitting on Distilled Datasets
by: Zhong, Xuyang, et al.
Published: (2023)

How to Mitigate Overfitting in Weak-to-strong Generalization?
by: Shi, Junhao, et al.
Published: (2025)

Residual Stream Analysis of Overfitting And Structural Disruptions
by: Liu, Quan, et al.
Published: (2026)

Consequentialist Objectives and Catastrophe
by: Marklund, Henrik, et al.
Published: (2026)

Adversarial Training: A Survey
by: Zhao, Mengnan, et al.
Published: (2024)

A Classical View on Benign Overfitting: The Role of Sample Size
by: Park, Junhyung, et al.
Published: (2025)

Friend or Foe? Harnessing Controllable Overfitting for Anomaly Detection
by: Qian, Long, et al.
Published: (2024)

On the Implicit Reward Overfitting and the Low-rank Dynamics in RLVR
by: Ye, Hao, et al.
Published: (2026)

Detecting Generative Parroting through Overfitting Masked Autoencoders
by: Taghanaki, Saeid Asgari, et al.
Published: (2024)

ETAGE: Enhanced Test Time Adaptation with Integrated Entropy and Gradient Norms for Robust Model Performance
by: Shamsi, Afshar, et al.
Published: (2024)

ECPv2: Fast, Efficient, and Scalable Global Optimization of Lipschitz Functions
by: Fourati, Fares, et al.
Published: (2025)

Eliminating Catastrophic Overfitting Via Abnormal Adversarial Examples Regularization
by: Lin, Runqi, et al.
Published: (2024)

Revisiting the Relationship between Adversarial and Clean Training: Why Clean Training Can Make Adversarial Training Better
by: Zhou, MingWei, et al.
Published: (2025)

TFGN: Task-Free, Replay-Free Continual Pre-Training Without Catastrophic Forgetting at LLM Scale
by: Ganguli, Anurup
Published: (2026)

Countering adversarial perturbations in graphs using error correcting codes
by: Jabari, Saif Eddin
Published: (2024)

LoRA Dropout as a Sparsity Regularizer for Overfitting Control
by: Lin, Yang, et al.
Published: (2024)

Conflict-Aware Adversarial Training
by: Xue, Zhiyu, et al.
Published: (2024)