Statistical analysis and parameter selection for Mapper
From MaRDI portal
Publication:4558149
zbMATH Open1444.62172arXiv1706.00204MaRDI QIDQ4558149FDOQ4558149
Authors: Mathieu Carrière, Bertrand Michel, Steve Y. Oudot 
Publication date: 21 November 2018
Abstract: In this article, we study the question of the statistical convergence of the 1-dimensional Mapper to its continuous analogue, the Reeb graph. We show that the Mapper is an optimal estimator of the Reeb graph, which gives, as a byproduct, a method to automatically tune its parameters and compute confidence regions on its topological features, such as its loops and flares. This allows to circumvent the issue of testing a large grid of parameters and keeping the most stable ones in the brute-force setting, which is widely used in visualization, clustering and feature selection with the Mapper.
Full work available at URL: https://arxiv.org/abs/1706.00204
Recommendations
- Statistical analysis of Mapper for stochastic and multivariate filters
- Probabilistic convergence and stability of random mapper graphs
- Structure and stability of the one-dimensional Mapper
- Structure and stability of the 1-dimensional mapper
- Convergence between categorical representations of Reeb space and mapper
Cites Work
- The elements of statistical learning. Data mining, inference, and prediction
- Confidence sets for persistence diagrams
- Convergence rates for persistence diagram estimation in topological data analysis
- The structure and stability of persistence modules
- Computational topology. An introduction
- On boundary estimation
- Geometric inference for probability measures
- Stability of persistence diagrams
- Title not available (Why is that?)
- Title not available (Why is that?)
- The edit distance for Reeb graphs of surfaces
- Measuring distance between Reeb graphs (extended abstract)
- Strong equivalence of the interleaving and functional distortion metrics for Reeb graphs
- Title not available (Why is that?)
- Manifold estimation and singular deconvolution under Hausdorff loss
- Extending persistence using Poincaré and Lefschetz duality
- Reeb graphs for shape analysis and applications
- Rates of convergence for robust geometric inference
- Categorified Reeb graphs
- Learning Theory
- On the Eigenspectrum of the Gram Matrix and the Generalization Error of Kernel-PCA
- Minimax manifold estimation
- PCA-kernel estimation
- Reeb graphs: approximation and persistence
- Convergence between categorical representations of Reeb space and mapper
- Local equivalence and intrinsic metrics between Reeb graphs
- Robust topological inference: distance to a measure and kernel distance
- Efficient and robust persistent homology for measures
- Topological analysis of nerves, Reeb spaces, mappers, and multiscale mappers
- Persistence theory. From quiver representations to data analysis
- Structure and stability of the 1-dimensional mapper
Cited In (16)
- Title not available (Why is that?)
- Structure and stability of the 1-dimensional mapper
- Structure and stability of the one-dimensional Mapper
- A gradient sampling algorithm for stratified maps with applications to topological data analysis
- Statistical embedding: beyond principal components
- Certified mapper: repeated testing for acyclicity and obstructions to the nerve lemma
- Some geometric and topological data-driven methods in robot motion path planning
- Mapper
- Topological data analysis and its usefulness for precision medicine studies
- Topological data analysis of single-cell Hi-C contact maps
- Topological mapper for 3D volumetric images
- Stitch fix for mapper and topological gains
- Statistical analysis of Mapper for stochastic and multivariate filters
- Ensemble Mapper
- Probabilistic convergence and stability of random mapper graphs
- Algebra, geometry and topology of ERK kinetics
Uses Software
This page was built for publication: Statistical analysis and parameter selection for Mapper
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4558149)
