Image de couverture de livre

When and Why Adversarial Training Improves PINNs: A Neural Tangent Kernel Perspective

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Cao, Yuan-dong, SO, Chi Chiu, Wang, Jun-Min, Wang, He
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

When Training-Free NAS Meets Vision Transformer: A Neural Tangent Kernel Perspective
par: Zhou, Qiqi, et autres
Publié: (2024)

Parameter-Efficient Fine-Tuning for Continual Learning: A Neural Tangent Kernel Perspective
par: Liu, Jingren, et autres
Publié: (2024)

Improving Clean Accuracy via a Tangent-Space Perspective on Adversarial Training
par: Yi, Bongsoo, et autres
Publié: (2024)

NTKMTL: Mitigating Task Imbalance in Multi-Task Learning from Neural Tangent Kernel Perspective
par: Qin, Xiaohan, et autres
Publié: (2025)

Fast Graph Condensation with Structure-based Neural Tangent Kernel
par: Wang, Lin, et autres
Publié: (2023)

Divergence of Empirical Neural Tangent Kernel in Classification Problems
par: Yu, Zixiong, et autres
Publié: (2025)

Differential Privacy Mechanisms in Neural Tangent Kernel Regression
par: Gu, Jiuxiang, et autres
Publié: (2024)

The Positivity of the Neural Tangent Kernel
par: Carvalho, Luís, et autres
Publié: (2024)

Mask-PINNs: Mitigating Internal Covariate Shift in Physics-Informed Neural Networks
par: Jiang, Feilong, et autres
Publié: (2025)

Noisy PDE Training Requires Bigger PINNs
par: Andre-Sloan, Sebastien, et autres
Publié: (2025)

Revisiting the Relationship between Adversarial and Clean Training: Why Clean Training Can Make Adversarial Training Better
par: Zhou, MingWei, et autres
Publié: (2025)

Annealing Self-Distillation Rectification Improves Adversarial Training
par: Wu, Yu-Yu, et autres
Publié: (2023)

Unveiling the Mechanism of Continuous Representation Full-Waveform Inversion: A Wave Based Neural Tangent Kernel Framework
par: Chen, Ruihua, et autres
Publié: (2026)

Path-Coordinated Continual Learning with Neural Tangent Kernel-Justified Plasticity: A Theoretical Framework with Near State-of-the-Art Performance
par: Shit, Rathin Chandra
Publié: (2025)

Why the Maximum Second Derivative of Activations Matters for Adversarial Robustness
par: Yu, Yunrui, et autres
Publié: (2026)

Understanding Emergent In-Context Learning from a Kernel Regression Perspective
par: Han, Chi, et autres
Publié: (2023)

Fast Neural Tangent Kernel Alignment, Norm and Effective Rank via Trace Estimation
par: Hazelden, James
Publié: (2025)

Decentralized Adversarial Training over Graphs
par: Cao, Ying, et autres
Publié: (2023)

Conflict-Aware Adversarial Training
par: Xue, Zhiyu, et autres
Publié: (2024)

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond
par: Ke, Yekun, et autres
Publié: (2024)

Norm-Hierarchy Transitions in Representation Learning: When and Why Neural Networks Abandon Shortcuts
par: Khanh, Truong Xuan, et autres
Publié: (2026)

Understanding and Improving Adversarial Robustness of Neural Probabilistic Circuits
par: Chen, Weixin, et autres
Publié: (2025)

Adversarial Training for Process Reward Models
par: Juneja, Gurusha, et autres
Publié: (2025)

Adversarial Training: A Survey
par: Zhao, Mengnan, et autres
Publié: (2024)

Align Your Tangent: Training Better Consistency Models via Manifold-Aligned Tangents
par: Kim, Beomsu, et autres
Publié: (2025)

IDInit: A Universal and Stable Initialization Method for Neural Network Training
par: Pan, Yu, et autres
Publié: (2025)

Adversarial Generative Flow Network for Solving Vehicle Routing Problems
par: Zhang, Ni, et autres
Publié: (2025)

Benign Overfitting in Adversarial Training for Vision Transformers
par: Zhang, Jiaming, et autres
Publié: (2026)

Why Do Neural Networks Forget: A Study of Collapse in Continual Learning
par: Zhu, Yunqin, et autres
Publié: (2026)

AscendKernelGen: A Systematic Study of LLM-Based Kernel Generation for Neural Processing Units
par: Cao, Xinzi, et autres
Publié: (2026)

Rethinking Invariance Regularization in Adversarial Training to Improve Robustness-Accuracy Trade-off
par: Waseda, Futa, et autres
Publié: (2024)

CKGAN: Training Generative Adversarial Networks Using Characteristic Kernel Integral Probability Metrics
par: Zhang, Kuntian, et autres
Publié: (2025)

Higher-order-ReLU-KANs (HRKANs) for solving physics-informed neural networks (PINNs) more accurately, robustly and faster
par: So, Chi Chiu, et autres
Publié: (2024)

Fast-Slow Co-advancing Optimizer: Toward Harmonious Adversarial Training of GAN
par: Wang, Lin, et autres
Publié: (2025)

Why Rectified Power Unit Networks Fail and How to Improve It: An Effective Field Theory Perspective
par: Kim, Taeyoung, et autres
Publié: (2024)

On the Rate of Convergence of GD in Non-linear Neural Networks: An Adversarial Robustness Perspective
par: Smorodinsky, Guy, et autres
Publié: (2026)

Ignition Phase : Standard Training for Fast Adversarial Robustness
par: Yu-Hang, Wang, et autres
Publié: (2025)

Online Adversarial Knowledge Distillation for Graph Neural Networks
par: Wang, Can, et autres
Publié: (2021)

Adversarial Instance Generation and Robust Training for Neural Combinatorial Optimization with Multiple Objectives
par: Liu, Wei, et autres
Publié: (2026)

Scalable Neural Network Kernels
par: Sehanobish, Arijit, et autres
Publié: (2023)