Convergence rates for persistence diagram estimation in Topological Data Analysis

Authors: Frédéric Chazal, Marc Glisse, Catherine Labruère, Bertrand Michel

ICML 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Some numerical experiments are performed in various contexts to illustrate our results.
Researcher Affiliation Academia Fr ed eric Chazal FREDERIC.CHAZAL@INRIA.FR INRIA Saclay ˆIle-de-France, Palaiseau, France Marc Glisse MARC.GLISSE@INRIA.FR INRIA Saclay ˆIle-de-France, Palaiseau, France Catherine Labru ere CLABRUER@U-BOURGOGNE.FR Institut de Math ematiques de Bourgogne, France Bertrand Michel BERTRAND.MICHEL@UPMC.FR LSTA, Universit e Pierre et Marie Curie, Paris
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any explicit statements about releasing source code or links to a code repository for the methodology described.
Open Datasets Yes M2 is a space of images: we used a 3D character from the SCAPE database (Anguelov et al., 2005)
Dataset Splits No The paper describes generating data through sampling ('sampled k sets of n points') and uses these samples for estimation and illustration of theoretical results, but it does not specify or mention any training, validation, or test dataset splits.
Hardware Specification No The paper does not provide any specific details about the hardware (e.g., CPU, GPU models, or memory) used to conduct the experiments described.
Software Dependencies No The paper does not list specific software dependencies with version numbers (e.g., programming languages, libraries, or solvers) used for its implementation or experiments.
Experiment Setup Yes From each of the measured metric spaces M1 and M2, we sampled k sets of n points for different values of n from which we computed persistence diagrams for different geometric complexes (see Table 1). For M1 we have computed the persistence diagrams for the 1-dimensional homology of the α-complex built on top of the sampled sets. For M2, we computed the persistence diagrams for the 1-dimensional homology of the Vietoris-Rips complex built on top of the sampled sets.