Some new methods to build group equivariant non-expansive operators in TDA

DOI10.1007/978-981-16-0174-3_19zbMATH Open1484.55006arXiv2010.08823OpenAlexW3203516453MaRDI QIDQ2067342FDOQ2067342

Authors: Nicola Quercioli 

Publication date: 18 January 2022

Abstract: Group equivariant operators are playing a more and more relevant role in machine learning and topological data analysis. In this paper we present some new results concerning the construction of $G$-equivariant non-expansive operators (GENEOs) from a space $varPhi$ of real-valued bounded continuous functions on a topological space $X$ to $varPhi$ itself. The space $varPhi$ represents our set of data, while $G$ is a subgroup of the group of all self-homeomorphisms of $X$, representing the invariance we are interested in.

Full work available at URL: https://arxiv.org/abs/2010.08823

Recommendations

• \(G\)-invariant persistent homology
• Combining persistent homology and invariance groups for shape comparison
• Homogeneous vector bundles and \(G\)-equivariant convolutional neural networks
• An introduction to the notion of natural pseudo-distance in topological data analysis
• Geometric metrics for topological representations

zbMATH Keywords

persistent homologypersistence diagramtopological data analysisgroup actionfiltering functionnatural pseudo-distancegroup equivariant non-expansive operator

Mathematics Subject Classification ID

Persistent homology and applications, topological data analysis (55N31) Computer graphics; computational geometry (digital and algorithmic aspects) (68U05) Topological data analysis (62R40)

Cites Work

• Persistent homology -- a survey
• Topology and data
• Combining persistent homology and invariance groups for shape comparison
• On invariance and selectivity in representation learning
• Persistent homology: theory and practice

Cited In (2)

• \(G\)-invariant persistent homology
• On the finite representation of linear group equivariant operators via permutant measures

Uses Software

• RotEqNet

This page was built for publication: Some new methods to build group equivariant non-expansive operators in TDA

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2067342)