Convolutional spectral kernel learning with generalization guarantees

DOI10.1016/J.ARTINT.2022.103803MaRDI QIDQ2093403zbMATH OpenOpenAlexFDO

Authors 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)

Recommendations

• Group invariance, stability to deformations, and complexity of deep convolutional representations
• Multiple spectral kernel learning and a Gaussian complexity computation
• Universality of deep convolutional neural networks
• Learning with generalization capability by kernel methods of bounded complexity
• Analysis of convolutional neural network image classifiers in a hierarchical max-pooling model with additional local pooling

Cites work

• 10.1162/153244303321897690
• A Mathematical Theory of Deep Convolutional Neural Networks for Feature Extraction
• Group invariance, stability to deformations, and complexity of deep convolutional representations
• Group invariant scattering
• Interpolation of spatial data. Some theory for kriging
• Large scale multiple kernel learning
• Local Rademacher complexities
• Local Rademacher complexity: sharper risk bounds with and without unlabeled samples
• On the equivalence between kernel quadrature rules and random feature expansions
• Rademacher penalties and structural risk minimization
• Theory of deep convolutional neural networks: downsampling
• Universality of deep convolutional neural networks

Describes a project that uses

Uses Software

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

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

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2093403)