Approximating continuous functions on persistence diagrams using template functions
From MaRDI portal
Abstract: The persistence diagram is an increasingly useful tool from Topological Data Analysis, but its use alongside typical machine learning techniques requires mathematical finesse. The most success to date has come from methods that map persistence diagrams into vector spaces, in a way which maximizes the structure preserved. This process is commonly referred to as featurization. In this paper, we describe a mathematical framework for featurization called emph{template functions}, and we show that it addresses the problem of approximating continuous functions on compact subsets of the space of persistence diagrams. Specifically, we begin by characterizing relative compactness with respect to the bottleneck distance, and then provide explicit theoretical methods for constructing compact-open dense subsets of continuous functions on persistence diagrams. These dense subsets -- obtained via template functions -- are leveraged for supervised learning tasks with persistence diagrams. Specifically, we test the method for classification and regression algorithms on several examples including shape data and dynamical systems.
Recommendations
- Topological machine learning with persistence indicator functions
- Persistence curves: a canonical framework for summarizing persistence diagrams
- Persistence images: a stable vector representation of persistent homology
- Persistence diagrams with linear machine learning models
- Proximity of persistence modules and their diagrams
Cites work
- scientific article; zbMATH DE number 1022658 (Why is no real title available?)
- scientific article; zbMATH DE number 7559221 (Why is no real title available?)
- A new test for chaos in deterministic systems
- Barycentric Lagrange Interpolation
- Confidence sets for persistence diagrams
- Decomposition of pointwise finite-dimensional persistence modules.
- Ergodic theory of chaos and strange attractors
- Fréchet means for distributions of persistence diagrams
- Functional summaries of persistence diagrams
- Kernel method for persistence diagrams via kernel embedding and weight factor
- Lyapunov characteristic exponents for smooth dynamical systems and for Hamiltonian systems; a method for computing all of them. I: Theory
- Nonembeddability of persistence diagrams with \(p>2\) Wasserstein metric
- On computing Poincaré map by Hénon method
- On the numerical computation of Poincaré maps
- On the validity of the 0–1 test for chaos
- Persistence images: a stable vector representation of persistent homology
- Probabilistic Fréchet means for time varying persistence diagrams
- Probability measures on the space of persistence diagrams
- Robust statistics, hypothesis testing, and confidence intervals for persistent homology on metric measure spaces
- Sampling from a Manifold
- Stability of persistence diagrams
- Statistical topological data analysis using persistence landscapes
- Stochastic convergence of persistence landscapes and silhouettes
- Symmetric and \(r\)-symmetric tropical polynomials and rational functions
- The ring of algebraic functions on persistence bar codes
- The structure and stability of persistence modules
- The theory of the interleaving distance on multidimensional persistence modules
- Time lagged ordinal partition networks for capturing dynamics of continuous dynamical systems
- Topological spaces of persistence modules and their properties
- Tropical coordinates on the space of persistence barcodes
- Understanding the topology and the geometry of the space of persistence diagrams via optimal partial transport
- Universality of persistence diagrams and the bottleneck and Wasserstein distances
- Zigzag persistence
Cited in
(6)- Embeddings of persistence diagrams into Hilbert spaces
- Describing topology on the set of persistence diagrams
- Rigorous cubical approximation and persistent homology of continuous functions
- Topological and metric properties of spaces of generalized persistence diagrams
- A pipeline for data-driven learning of topological features with applications to protein stability prediction
- On the space of generalized persistence diagrams
This page was built for publication: Approximating continuous functions on persistence diagrams using template functions
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6047301)
