Imagen de Portada

Incorruptible Neural Networks: Training Models that can Generalize to Large Internal Perturbations

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Jacobson, Philip, Feinberg, Ben, Kumar, Suhas, Agarwal, Sapan, Xiao, T. Patrick, Bennett, Christopher
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Analog Bayesian neural networks are insensitive to the shape of the weight distribution
por: Patel, Ravi G., et al.
Publicado: (2025)

Modeling Causal Mechanisms with Diffusion Models for Interventional and Counterfactual Queries
por: Chao, Patrick, et al.
Publicado: (2023)

TED: Accelerate Model Training by Internal Generalization
por: Xiao, Jinying, et al.
Publicado: (2024)

Synthetic Combinations: A Causal Inference Framework for Combinatorial Interventions
por: Agarwal, Abhineet, et al.
Publicado: (2023)

Strengthening the Internal Adversarial Robustness in Lifted Neural Networks
por: Zach, Christopher
Publicado: (2025)

Node Perturbation Can Effectively Train Multi-Layer Neural Networks
por: Dalm, Sander, et al.
Publicado: (2023)

Gradient-Free Training of Recurrent Neural Networks using Random Perturbations
por: Fernandez, Jesus Garcia, et al.
Publicado: (2024)

Provably Bounding Neural Network Preimages
por: Kotha, Suhas, et al.
Publicado: (2023)

Improving Line Search Methods for Large Scale Neural Network Training
por: Kenneweg, Philip, et al.
Publicado: (2024)

Revisiting LARS for Large Batch Training Generalization of Neural Networks
por: Do, Khoi, et al.
Publicado: (2023)

G-RepsNet: A Fast and General Construction of Equivariant Networks for Arbitrary Matrix Groups
por: Basu, Sourya, et al.
Publicado: (2024)

Quantifying Explanation Quality in Graph Neural Networks using Out-of-Distribution Generalization
por: Zhang, Ding, et al.
Publicado: (2026)

SPIRE: Conditional Personalization for Federated Diffusion Generative Models
por: Ozkara, Kaan, et al.
Publicado: (2025)

Training Feedforward Neural Networks with Bayesian Hyper-Heuristics
por: Schreuder, Arné, et al.
Publicado: (2023)

A Methodology-Oriented Study of Catastrophic Forgetting in Incremental Deep Neural Networks
por: Kumar, Ashutosh, et al.
Publicado: (2024)

Benchmarking Neural Network Training Algorithms
por: Dahl, George E., et al.
Publicado: (2023)

DARTH-PUM: A Hybrid Processing-Using-Memory Architecture
por: Wong, Ryan, et al.
Publicado: (2026)

A Unified Physics-Informed Neural Network for Modeling Coupled Electro- and Elastodynamic Wave Propagation Using Three-Stage Loss Optimization
por: Bharadwaj, Suhas Suresh, et al.
Publicado: (2026)

Gradient Perturbation: Learning to Perturb Gradients for Adaptive Training
por: Li, Hua
Publicado: (2026)

Heating Up Quasi-Monte Carlo Graph Random Features: A Diffusion Kernel Perspective
por: Feinberg, Brooke, et al.
Publicado: (2024)

Neural Clamping: Joint Input Perturbation and Temperature Scaling for Neural Network Calibration
por: Tang, Yung-Chen, et al.
Publicado: (2022)

Wide Two-Layer Networks can Learn from Adversarial Perturbations
por: Kumano, Soichiro, et al.
Publicado: (2024)

Convolutional Neural Networks can achieve binary bail judgement classification
por: Barman, Amit, et al.
Publicado: (2024)

On Discprecncies between Perturbation Evaluations of Graph Neural Network Attributions
por: Rezaei, Razieh, et al.
Publicado: (2024)

GIN-Graph: A Generative Interpretation Network for Model-Level Explanation of Graph Neural Networks
por: Yue, Xiao, et al.
Publicado: (2025)

Gradient Flow Matching for Learning Update Dynamics in Neural Network Training
por: Shou, Xiao, et al.
Publicado: (2025)

Unifying Adversarial Perturbation for Graph Neural Networks
por: Yang, Jinluan, et al.
Publicado: (2025)

FutureFill: Fast Generation from Convolutional Sequence Models
por: Agarwal, Naman, et al.
Publicado: (2024)

Vecchia Gaussian Process Ensembles on Internal Representations of Deep Neural Networks
por: Jimenez, Felix, et al.
Publicado: (2023)

On the Dataless Training of Neural Networks
por: Velasquez, Alvaro, et al.
Publicado: (2025)

Generative Intervention Models for Causal Perturbation Modeling
por: Schneider, Nora, et al.
Publicado: (2024)

LOGIN: A Large Language Model Consulted Graph Neural Network Training Framework
por: Qiao, Yiran, et al.
Publicado: (2024)

APEX: Probing Neural Networks via Activation Perturbation
por: Ren, Tao, et al.
Publicado: (2026)

Implicit Generative Prior for Bayesian Neural Networks
por: Liu, Yijia, et al.
Publicado: (2024)

Enhancing Signed Graph Neural Networks through Curriculum-Based Training
por: Zhang, Zeyu, et al.
Publicado: (2023)

Training Large Neural Networks With Low-Dimensional Error Feedback
por: Hanut, Maher, et al.
Publicado: (2025)

Training Robust Graph Neural Networks by Modeling Noise Dependencies
por: In, Yeonjun, et al.
Publicado: (2025)

RL-ACRGNet: Reinforcement Learning-Based Chest Radiology Report Generation Network
por: Meena, Yogesh Kumar, et al.
Publicado: (2026)

Beyond Scaling Curves: Internal Dynamics of Neural Networks Through the NTK Lens
por: Nikolaou, Konstantin, et al.
Publicado: (2025)

From Weight Perturbation to Feature Attribution for Explaining Fully Connected Neural Networks
por: Lymperopoulos, Thodoris, et al.
Publicado: (2026)