Searcharxiv⌕ Search

arXiv subjects

Francisco Belchí

Publications and source records attributed to Francisco Belchí.

4 recordsLinked to original sources
arXiv2019

A numerical measure of the instability of Mapper-type algorithms

Mapper is an unsupervised machine learning algorithm generalising the notion of clustering to obtain a geometric description of a dataset. The procedure splits the data into possibly overlapping bins which are then clustered. The output of the algorithm is a graph where nodes represent clusters and edges represent the sharing of data points between two clusters. However, several parameters must be selected before applying Mapper and the resulting graph may vary dramatically with the choice of parameters. We define an intrinsic notion of Mapper instability that measures the variability of the output as a function of the choice of parameters required to construct a Mapper output. Our results and discussion are general and apply to all Mapper-type algorithms. We derive theoretical results that provide estimates for the instability and suggest practical ways to control it. We provide also experiments to illustrate our results and in particular we demonstrate that a reliable candidate Mapper output can be identified as a local minimum of instability regarded as a function of Mapper input parameters.

math.AT↗
arXiv2019

$A_\infty$ persistent homology estimates the topology from pointcloud datasets

Let $X$ be a closed subspace of a metric space $M$. Under mild hypotheses, one can estimate the Betti numbers of $X$ from a finite set $P \subset M$ of points approximating $X$. In this paper, we show that one can also use $P$ to estimate much more detailed topological properties of $X$. These properties are computed via $A_\infty$-structures, and are therefore related to the cup and Massey products of $X$, its loop space $ΩX$, its formality, linking numbers, etc. Additionally, we study the following setting: given a continuous function $f \colon Y \longrightarrow \mathbb R$ on a topological space $Y$, $A_\infty$ persistent homology builds a family of barcodes presenting a highly detailed description of some geometric and topological properties of $Y$. We prove here that under mild assumptions, these barcodes are stable: small perturbations in the function $f$ imply at most small perturbations in the barcodes.

math.AT↗
arXiv2017

Optimising the topological information of the $A_\infty$-persistence groups

Persistent homology typically studies the evolution of homology groups $H_p(X)$ (with coefficients in a field) along a filtration of topological spaces. $A_\infty$-persistence extends this theory by analysing the evolution of subspaces such as $V := \text{Ker}\, {Δ_n}_{| H_p(X)} \subseteq H_p(X)$, where $\{Δ_m\}_{m\geq1}$ denotes a structure of $A_\infty$-coalgebra on $H_*(X)$. In this paper we illustrate how $A_\infty$-persistence can be useful beyond persistent homology by discussing the topological meaning of $V$, which is the most basic form of $A_\infty$-persistence group. In addition, we explore how to choose $A_\infty$-coalgebras along a filtration to make the $A_\infty$-persistence groups carry more faithful information.

math.AT↗