DeepAI AI Chat
Log In Sign Up

TOAST: Topological Algorithm for Singularity Tracking

by   Julius von Rohrscheidt, et al.

The manifold hypothesis, which assumes that data lie on or close to an unknown manifold of low intrinsic dimensionality, is a staple of modern machine learning research. However, recent work has shown that real-world data exhibit distinct non-manifold structures, which result in singularities that can lead to erroneous conclusions about the data. Detecting such singularities is therefore crucial as a precursor to interpolation and inference tasks. We address detecting singularities by developing (i) persistent local homology, a new topology-driven framework for quantifying the intrinsic dimension of a data set locally, and (ii) Euclidicity, a topology-based multi-scale measure for assessing the 'manifoldness' of individual points. We show that our approach can reliably identify singularities of complex spaces, while also capturing singular structures in real-world data sets.


page 10

page 18

page 19


Topological Autoencoders

We propose a novel approach for preserving topological structures of the...

Estimate of the Neural Net Dimension Using Algebraic Topology and Lie Theory

In this paper we present an approach to determine the smallest possible ...

Estimate of the Neural Network Dimension Using Algebraic Topology and Lie Theory

In this paper, we present an approach to determine the smallest possible...

MESS: Manifold Embedding Motivated Super Sampling

Many approaches in the field of machine learning and data analysis rely ...

Heuristic Framework for Multi-Scale Testing of the Multi-Manifold Hypothesis

When analyzing empirical data, we often find that global linear models o...

A flexible outlier detector based on a topology given by graph communities

Outlier, or anomaly, detection is essential for optimal performance of m...

Multiscale Manifold Warping

Many real-world applications require aligning two temporal sequences, in...