Convolutional spectral kernel learning with generalization guarantees

DOI10.1016/j.artint.2022.103803OpenAlexW4300717047MaRDI QIDQ2093403

Yanyan Li

Publication date: 8 November 2022

Published in: Artificial Intelligence (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.artint.2022.103803

zbMATH Keywords

Rademacher complexitygeneralization analysisconvolutional operatorcosine activationnon-stationary spectral kernel

Mathematics Subject Classification ID

Artificial intelligence (68Txx)

Uses Software

• SHOGUN
• PyTorch
• ImageNet
• Adam
• AlexNet
• ShuffleNet

Cites Work

• Unnamed Item
• Unnamed Item
• Interpolation of spatial data. Some theory for kriging
• Local Rademacher complexity: sharper risk bounds with and without unlabeled samples
• Theory of deep convolutional neural networks: downsampling
• Universality of deep convolutional neural networks
• Local Rademacher complexities
• Group Invariant Scattering
• Rademacher penalties and structural risk minimization
• A Mathematical Theory of Deep Convolutional Neural Networks for Feature Extraction
• 10.1162/153244303321897690
• On the Equivalence between Kernel Quadrature Rules and Random Feature Expansions

This page was built for publication: Convolutional spectral kernel learning with generalization guarantees