DeepAI AI Chat
Log In Sign Up

Statistical learning on measures: an application to persistence diagrams

by   Olympio Hacquard, et al.

We consider a binary supervised learning classification problem where instead of having data in a finite-dimensional Euclidean space, we observe measures on a compact space 𝒳. Formally, we observe data D_N = (μ_1, Y_1), …, (μ_N, Y_N) where μ_i is a measure on 𝒳 and Y_i is a label in {0, 1}. Given a set ℱ of base-classifiers on 𝒳, we build corresponding classifiers in the space of measures. We provide upper and lower bounds on the Rademacher complexity of this new class of classifiers that can be expressed simply in terms of corresponding quantities for the class ℱ. If the measures μ_i are uniform over a finite set, this classification task boils down to a multi-instance learning problem. However, our approach allows more flexibility and diversity in the input data we can deal with. While such a framework has many possible applications, this work strongly emphasizes on classifying data via topological descriptors called persistence diagrams. These objects are discrete measures on ℝ^2, where the coordinates of each point correspond to the range of scales at which a topological feature exists. We will present several classifiers on measures and show how they can heuristically and theoretically enable a good classification performance in various settings in the case of persistence diagrams.


page 1

page 2

page 3

page 4


Learning on Persistence Diagrams as Radon Measures

Persistence diagrams are common descriptors of the topological structure...

PersLay: A Neural Network Layer for Persistence Diagrams and New Graph Topological Signatures

Persistence diagrams, the most common descriptors of Topological Data An...

Understanding the Topology and the Geometry of the Persistence Diagram Space via Optimal Partial Transport

We consider a generalization of persistence diagrams, namely Radon measu...

The density of expected persistence diagrams and its kernel based estimation

Persistence diagrams play a fundamental role in Topological Data Analysi...

A Convolutional Persistence Transform

We consider a new topological feauturization of d-dimensional images, ob...

ATOL: Measure Vectorisation for Automatic Topologically-Oriented Learning

Robust topological information commonly comes in the form of a set of pe...

A General Neural Network Architecture for Persistence Diagrams and Graph Classification

Graph classification is a difficult problem that has drawn a lot of atte...

Code Repositories