deep-neural-networks

Tag

Cards List
#deep-neural-networks

Mitigating the Curse of Dimensionality in Uniform Convergence of Deep Neural Networks via Smooth Activations

arXiv cs.LG · 2d ago Cached

This paper establishes a theoretical framework showing that smooth activations in deep neural networks can mitigate the curse of dimensionality in uniform convergence, providing non-asymptotic guarantees and outperforming ReLU networks in worst-case reliability.

0 favorites 0 likes
#deep-neural-networks

Pruning Deep Neural Networks via the Marchenko--Pastur Distribution

arXiv cs.LG · 4d ago Cached

This paper presents a Marchenko-Pastur random matrix approach to pruning deep neural networks, offering theoretical guarantees and achieving strong accuracy retention with minimal fine-tuning on ImageNet for ViT and CNN architectures.

0 favorites 0 likes
#deep-neural-networks

Variational Inference for Evidential Deep Learning

arXiv cs.LG · 2026-05-27 Cached

A mathematically principled framework, Variational Inference Evidential Deep Learning (VI-EDL), is proposed to address limitations in conventional Evidential Deep Learning by reformulating it through variational inference, deriving an Evidence Lower Bound, establishing a generalization bound, and achieving state-of-the-art performance on visual and medical datasets.

0 favorites 0 likes
#deep-neural-networks

CAFD: Concept-Aware DNN Fault Detection using VLMs

arXiv cs.LG · 2026-05-26 Cached

This paper introduces CAFD, a learning-based approach for DNN fault detection that integrates model-based, distance-based, and a novel concept-based feature called Concept Failure Ratio (CFR) derived from Vision-Language Models. CAFD consistently outperforms state-of-the-art baselines in fault detection rate across multiple datasets and budgets.

0 favorites 0 likes
#deep-neural-networks

SoK: A Comprehensive Analysis of the Current Status of Neural Tangent Generalization Attacks with Research Directions

arXiv cs.LG · 2026-05-14 Cached

This paper presents a comprehensive analysis of the Neural Tangent Generalization Attack (NTGA) for data protection, including a taxonomy of related attacks, and discusses future research directions.

0 favorites 0 likes
← Back to home

Submit Feedback