Corpus ID: 19807367

Sliced Wasserstein Kernel for Persistence Diagrams

@inproceedings{Carrire2017SlicedWK,
  title={Sliced Wasserstein Kernel for Persistence Diagrams},
  author={Mathieu Carri{\`e}re and Marco Cuturi and S. Oudot},
  booktitle={ICML},
  year={2017}
}

Mathieu Carrière, Marco Cuturi, S. Oudot

Published in ICML 2017

Computer Science, Mathematics

Persistence diagrams (PDs) play a key role in topological data analysis (TDA), in which they are routinely used to describe topological properties of complicated shapes. PDs enjoy strong stability properties and have proven their utility in various learning contexts. They do not, however, live in a space naturally endowed with a Hilbert structure and are usually compared with non-Hilbertian distances, such as the bottleneck distance. To incorporate PDs in a convex learning pipeline, several… CONTINUE READING

View PDF on arXiv

Save to Library

Create Alert

Cite

Launch Research Feed