PuSH - Publication Server of Helmholtz Zentrum München

Export: TXT Text RIS Endnote (RIS) BIB BibTeX
von Rohrscheidt, J.C. ; Rieck, B.

Topological Singularity Detection at Multiple Scales.

In: (Proceedings of Machine Learning Research). 2023. 35175-35197 (Proceedings of Machine Learning Research ; 202)
Publ. Version/Full Text
The manifold hypothesis, which assumes that data lies on or close to an unknown manifold of low intrinsic dimension, is a staple of modern machine learning research. However, recent work has shown that real-world data exhibits distinct non-manifold structures, i.e. singularities, that can lead to erroneous findings. Detecting such singularities is therefore crucial as a precursor to interpolation and inference tasks. We address this issue by developing a topological framework that (i) quantifies the local intrinsic dimension, and (ii) yields a Euclidicity score for assessing the 'manifoldness' of a point along multiple scales. Our approach identifies singularities of complex spaces, while also capturing singular structures and local geometric complexity in image data.
Tags
Annotations
Special Publikation
Hide on homepage

Edit extra information
Edit own tags
Private
Edit own annotation
Private
Hide on publication lists
on hompage
Mark as special
publikation
Publication type Article: Conference contribution
Language english
Publication Year 2023
HGF-reported in Year 2023
Conference Title Proceedings of Machine Learning Research
Quellenangaben Volume: 202, Issue: , Pages: 35175-35197 Article Number: , Supplement: ,
Institute(s) Institute of AI for Health (AIH)
POF-Topic(s) 30205 - Bioengineering and Digital Health
Research field(s) Enabling and Novel Technologies
PSP Element(s) G-540003-001
Scopus ID 85174423728
Erfassungsdatum 2023-11-28
[➜Report correction]