aiqbench analysis
This paper introduces transversal pooling neural networks, which extend spatial max pooling to handle affine group actions for improved stability against small input transformations. By deriving explicit bounds on wavelet coefficients and demonstrating utility in low-data scenarios like tropical cyclone prediction, the work advances theoretical machine learning architectures.
Transversal Pooling Neural Networks
arXiv:2609.36237v1 Announce Type: new Abstract: Many learning tasks require stability to small transformations while retaining sensitivity to larger ones. We introduce \emph{transversal pooling neural networks}, which generalize spatial max pooling to affine group actions. We establish equivariance to a chosen subgroup and derive explicit stability bounds for individual pooled wavelet coefficients under affine perturbations of the input. Experimentally, we demonstrate the utility of our networks in low-data environments and for predicting tropical cyclone intensification.
Abstract:Many learning tasks require stability to small transformations while retaining sensitivity to larger ones. We introduce \emph{transversal pooling neural networks}, which generalize spatial max pooling to affine group actions. We establish equivariance to a chosen subgroup and derive explicit stability bounds for individual pooled wavelet coefficients under affine perturbations of the input. Experimentally, we demonstrate the utility of our networks in low-data environments and for predicting tropical cyclone intensification.
Machine Learning (cs.LG); Functional Analysis (math.FA)
arXiv:2609.36237 [cs.LG]
(or arXiv:2609.36237v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2609.36237 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 166 words
Related coverage
Theoretical Aspects of Lie Groupoid and Lie Algebroid Equivariant Convolutional Neural Networks
arXiv · Jul 24, 2026
Theoretical Aspects of Lie Groupoid and Lie Algebroid Equivariant Convolutional Neural Networks
arXiv · Jun 3, 2026
WiMi Develops Quantum Kernel Convolution Method for NISQ Quantum Devices
The Quantum Insider · Jun 15, 2026
More Data, Worse Decisions? Preference Reversals in Neural Networks under Gram Incompatibility
arXiv · Jul 31, 2026