Imagen de Portada

Variance-Aware Noisy Training: Hardening DNNs against Unstable Analog Computations

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wang, Xiao, Borras, Hendrik, Klein, Bernhard, Fröning, Holger
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

On Hardening DNNs against Noisy Computations
por: Wang, Xiao, et al.
Publicado: (2025)

Walking Noise: On Layer-Specific Robustness of Neural Architectures against Noisy Computations and Associated Characteristic Learning Dynamics
por: Borras, Hendrik, et al.
Publicado: (2022)

Uncertainty-Preserving QBNNs: Multi-Level Quantization of SVI-Based Bayesian Neural Networks for Image Classification
por: Borras, Hendrik, et al.
Publicado: (2025)

Accelerated Execution of Bayesian Neural Networks using a Single Probabilistic Forward Pass and Code Generation
por: Klein, Bernhard, et al.
Publicado: (2025)

Function Space Diversity for Uncertainty Prediction via Repulsive Last-Layer Ensembles
por: Steger, Sophie, et al.
Publicado: (2024)

A Tabular Schedule Abstraction for Communication-Aware Evaluation of Pipeline-Parallel LLM Training
por: Barley, Daniel, et al.
Publicado: (2026)

Less Memory Means smaller GPUs: Backpropagation with Compressed Activations
por: Barley, Daniel, et al.
Publicado: (2024)

Resource-Efficient and Robust Inference of Deep and Bayesian Neural Networks on Embedded and Analog Computing Platforms
por: Klein, Bernhard
Publicado: (2025)

How Controlling the Variance can Improve Training Stability of Sparsely Activated DNNs and CNNs
por: Dent, Emily, et al.
Publicado: (2026)

Resource-Efficient Neural Networks for Embedded Systems
por: Roth, Wolfgang, et al.
Publicado: (2020)

Machine Unlearning for Robust DNNs: Attribution-Guided Partitioning and Neuron Pruning in Noisy Environments
por: Jin, Deliang, et al.
Publicado: (2025)

TinyTrain: Resource-Aware Task-Adaptive Sparse Training of DNNs at the Data-Scarce Edge
por: Kwon, Young D., et al.
Publicado: (2023)

Carbon Intensity-Aware Adaptive Inference of DNNs
por: Jung, Jiwan
Publicado: (2024)

Implications of Noise in Resistive Memory on Deep Neural Networks for Image Classification
por: Emonds, Yannick, et al.
Publicado: (2024)

Hessian-aware Training for Enhancing DNNs Resilience to Parameter Corruptions
por: Prato, Tahmid Hasan, et al.
Publicado: (2025)

ProAct: Progressive Training for Hybrid Clipped Activation Function to Enhance Resilience of DNNs
por: Mousavi, Seyedhamidreza, et al.
Publicado: (2024)

Variance-Aware Adaptive Weighting for Diffusion Model Training
por: Sun, Nanlong, et al.
Publicado: (2026)

Rapid Deployment of DNNs for Edge Computing via Structured Pruning at Initialization
por: Eccles, Bailey J., et al.
Publicado: (2024)

Denoising-Aware Contrastive Learning for Noisy Time Series
por: Zhou, Shuang, et al.
Publicado: (2024)

Theoretical Analysis of Robust Overfitting for Wide DNNs: An NTK Approach
por: Fu, Shaopeng, et al.
Publicado: (2023)

ReCycle: Resilient Training of Large DNNs using Pipeline Adaptation
por: Gandhi, Swapnil, et al.
Publicado: (2024)

Complexity of One-Dimensional ReLU DNNs
por: Kogan, Jonathan, et al.
Publicado: (2025)

HAWX: A Hardware-Aware FrameWork for Fast and Scalable ApproXimation of DNNs
por: Nazari, Samira, et al.
Publicado: (2026)

TroLLoc: Logic Locking and Layout Hardening for IC Security Closure against Hardware Trojans
por: Wang, Fangzhou, et al.
Publicado: (2024)

VASSO: Variance Suppression for Sharpness-Aware Minimization
por: Li, Bingcong, et al.
Publicado: (2025)

Towards Exact Gradient-based Training on Analog In-memory Computing
por: Wu, Zhaoxian, et al.
Publicado: (2024)

Unstable Rankings in Bayesian Deep Learning Evaluation
por: Zhan, Qishi, et al.
Publicado: (2026)

Mitigating Evasion Attacks in Fog Computing Resource Provisioning Through Proactive Hardening
por: Salmi, Younes, et al.
Publicado: (2026)

ForeCal: Random Forest-based Calibration for DNNs
por: Nigam, Dhruv
Publicado: (2024)

Deep Learning meets Nonparametric Regression: Are Weight-Decayed DNNs Locally Adaptive?
por: Zhang, Kaiqi, et al.
Publicado: (2022)

Koopman Theory-Inspired Method for Learning Time Advancement Operators in Unstable Flame Front Evolution
por: Yu, Rixin, et al.
Publicado: (2024)

Uncertainty-Aware Robust Learning on Noisy Graphs
por: Chen, Shuyi, et al.
Publicado: (2023)

On Background Bias of Post-Hoc Concept Embeddings in Computer Vision DNNs
por: Schwalbe, Gesina, et al.
Publicado: (2025)

Adversarial Resilience against Clean-Label Attacks in Realizable and Noisy Settings
por: Heinzler, Carolin
Publicado: (2025)

A Framework to Enable Algorithmic Design Choice Exploration in DNNs
por: Cronin IV, Timothy L., et al.
Publicado: (2024)

Expressivity of congruence-based architectures for DNNs on positive-definite matrices
por: Oswald, Antonin, et al.
Publicado: (2026)

Understanding DNNs in Feature Interaction Models: A Dimensional Collapse Perspective
por: Wang, Jiancheng, et al.
Publicado: (2026)

Compute-Optimal Quantization-Aware Training
por: Dremov, Aleksandr, et al.
Publicado: (2025)

CEAR: Certified Ensemble Adversarial Robustness in DNNs
por: Sadig, Daniel, et al.
Publicado: (2026)

Exploring Variance Reduction in Importance Sampling for Efficient DNN Training
por: Kutsuna, Takuro
Publicado: (2025)