Topological machine learning with persistence indicator functions
From MaRDI portal
Abstract: Techniques from computational topology, in particular persistent homology, are becoming increasingly relevant for data analysis. Their stable metrics permit the use of many distance-based data analysis methods, such as multidimensional scaling, while providing a firm theoretical ground. Many modern machine learning algorithms, however, are based on kernels. This paper presents persistence indicator functions (PIFs), which summarize persistence diagrams, i.e., feature descriptors in topological data analysis. PIFs can be calculated and compared in linear time and have many beneficial properties, such as the availability of a kernel-based similarity measure. We demonstrate their usage in common data analysis scenarios, such as confidence set estimation and classification of complex structured data.
Recommendations
- Persistence images: a stable vector representation of persistent homology
- Learning representations of persistence barcodes
- Kernel method for persistence diagrams via kernel embedding and weight factor
- Supervised learning with indefinite topological Kernels
- Persistence diagrams with linear machine learning models
Cites work
- Algorithms – ESA 2004
- Computational topology. An introduction
- Extreme elevation on a 2-manifold
- Fréchet means for distributions of persistence diagrams
- Geometry Helps to Compare Persistence Diagrams
- scientific article; zbMATH DE number 708500 (Why is no real title available?)
- scientific article; zbMATH DE number 1950576 (Why is no real title available?)
- Introduction to empirical processes and semiparametric inference
- Lipschitz functions have \(L_{p}\)-stable persistence
- Persistence images: a stable vector representation of persistent homology
- Scikit-learn: machine learning in Python
- Stability of persistence diagrams
- Statistical topological data analysis using persistence landscapes
- Topological persistence and simplification
- Topology of random geometric complexes: a survey
Cited in
(20)- Persistence diagrams with linear machine learning models
- Topological data analysis for the energy and stability of endohedral metallofullerenes
- Bayesian topological signal processing
- A stable cardinality distance for topological classification
- Persistence curves: a canonical framework for summarizing persistence diagrams
- Geometric metrics for topological representations
- Kernel method for persistence diagrams via kernel embedding and weight factor
- Interactions between kernels, frames, and persistent homology
- A persistent homological analysis of network data flow malfunctions
- \textit{giotto-tda}: a topological data analysis toolkit for machine learning and data exploration
- scientific article; zbMATH DE number 7368521 (Why is no real title available?)
- Shapley homology: topological analysis of sample influence for neural networks
- Hierarchies and Ranks for Persistence Pairs
- Learning representations of persistence barcodes
- Persistence images: a stable vector representation of persistent homology
- Approximating continuous functions on persistence diagrams using template functions
- Algebraic machine learning with an application to chemistry
- The magnitude vector of images
- Fast topological signal identification and persistent cohomological cycle matching
- Convolutional persistence transforms
This page was built for publication: Topological machine learning with persistence indicator functions
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5147730)
