Image de couverture de livre

Adversarially robust generalization theory via Jacobian regularization for deep neural networks

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wu, Dongya, Li, Xin
Format:	Preprint
Publié:	2024
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

Sparse deep neural networks for nonparametric estimation in high-dimensional sparse regression
par: Wu, Dongya, et autres
Publié: (2024)

Implicit regularization of deep residual networks towards neural ODEs
par: Marion, Pierre, et autres
Publié: (2023)

Are classical deep neural networks weakly adversarially robust?
par: Sun, Nuolin, et autres
Publié: (2025)

Beyond topography: Topographic regularization improves robustness and reshapes representations in convolutional neural networks
par: Truong, Nhut, et autres
Publié: (2025)

Improving deep neural network generalization and robustness to background bias via layer-wise relevance propagation optimization
par: Bassi, Pedro R. A. S., et autres
Publié: (2022)

On margin-based generalization prediction in deep neural networks
par: Mouton, Coenraad
Publié: (2024)

Controlling diverse robots by inferring Jacobian fields with deep networks
par: Li, Sizhe Lester, et autres
Publié: (2024)

Can overfitted deep neural networks in adversarial training generalize? -- An approximation viewpoint
par: Shi, Zhongjie, et autres
Publié: (2024)

Causal inference through multi-stage learning and doubly robust deep neural networks
par: Zhang, Yuqian, et autres
Publié: (2024)

RDI: An adversarial robustness evaluation metric for deep neural networks based on model statistical features
par: Song, Jialei, et autres
Publié: (2025)

A multiobjective continuation method to compute the regularization path of deep neural networks
par: Amakor, Augustina C., et autres
Publié: (2023)

Exploring the loss landscape of regularized neural networks via convex duality
par: Kim, Sungyoon, et autres
Publié: (2024)

InfoGNN: End-to-end deep learning on mesh via graph neural networks
par: Gao, Ling, et autres
Publié: (2025)

Intrinsic training dynamics of deep neural networks
par: Marcotte, Sibylle, et autres
Publié: (2025)

Towards generalizable deep ptychography neural networks
par: Vong, Albert, et autres
Publié: (2025)

An axiomatized PDE model of deep neural networks
par: Wang, Tangjun, et autres
Publié: (2023)

Memorization capacity of deep ReLU neural networks characterized by width and depth
par: Yang, Xin, et autres
Publié: (2026)

Learning time-dependent PDE via graph neural networks and deep operator network for robust accuracy on irregular grids
par: Cho, Sung Woong, et autres
Publié: (2024)

Spring-block theory of feature learning in deep neural networks
par: Shi, Cheng, et autres
Publié: (2024)

Outlier-robust neural network training: variation regularization meets trimmed loss to prevent functional breakdown
par: Okuno, Akifumi, et autres
Publié: (2023)

Distributionally robust approximation property of neural networks
par: Ceylan, Mihriban, et autres
Publié: (2025)

Deep neural networks for choice analysis: Enhancing behavioral regularity with gradient regularization
par: Feng, Siqi, et autres
Publié: (2024)

Detecting data-driven robust statistical arbitrage strategies with deep neural networks
par: Neufeld, Ariel, et autres
Publié: (2022)

Motif distribution and function of sparse deep neural networks
par: Zahn, Olivia T., et autres
Publié: (2024)

Infinite-channel deep stable convolutional neural networks
par: Bracale, Daniele, et autres
Publié: (2021)

Approximation and interpolation of deep neural networks
par: Constantinescu, Vlad-Raul, et autres
Publié: (2023)

Minimax optimality of deep neural networks on dependent data via PAC-Bayes bounds
par: Alquier, Pierre, et autres
Publié: (2024)

A constrained optimization approach to improve robustness of neural networks
par: Zhao, Shudian, et autres
Publié: (2024)

Adversarial generalization of unfolding (model-based) networks
par: Kouni, Vicky
Publié: (2025)

Dimensionality-induced information loss of outliers in deep neural networks
par: Uematsu, Kazuki, et autres
Publié: (2024)

An unsupervised tour through the hidden pathways of deep neural networks
par: Doimo, Diego
Publié: (2025)

Nonlinear spiked covariance matrices and signal propagation in deep neural networks
par: Wang, Zhichao, et autres
Publié: (2024)

Towards a theory of how the structure of language is acquired by deep neural networks
par: Cagnetta, Francesco, et autres
Publié: (2024)

A simple theory for training response of deep neural networks
par: Nakazato, Kenichi
Publié: (2024)

Invariant deep neural networks under the finite group for solving partial differential equations
par: Zhang, Zhi-Yong, et autres
Publié: (2024)

Experimental robustness benchmarking of quantum neural networks on a superconducting quantum processor
par: Zhang, Hai-Feng, et autres
Publié: (2025)

Conservative neural posterior estimation via distributionally robust training
par: Laplante, William, et autres
Publié: (2026)

On the VC dimension of deep group convolutional neural networks
par: Sepliarskaia, Anna, et autres
Publié: (2024)

Utilizing Lyapunov Exponents in designing deep neural networks
par: Mittra, Tirthankar
Publié: (2024)

Hybrid deep additive neural networks
par: Kim, Gyu Min, et autres
Publié: (2024)