Journal article
Persistence paths and signature features in topological data analysis
- Abstract:
-
We introduce a new feature map for barcodes as they arise in persistent homology computation. The main idea is to first realize each barcode as a path in a convenient vector space, and to then compute its path signature which takes values in the tensor algebra of that vector space. The composition of these two operations-barcode to path, path to tensor series-results in a feature map that has several desirable properties for statistical learning, such as universality and characteristicness, and achieves state-of-the-art results on common classification benchmarks.
- Publication status:
- Published
- Peer review status:
- Peer reviewed
Actions
Access Document
- Files:
-
-
(Preview, Accepted manuscript, pdf, 5.3MB, Terms of use)
-
- Publisher copy:
- 10.1109/TPAMI.2018.2885516
Authors
- Publisher:
- IEEE
- Journal:
- IEEE Transactions on Pattern Analysis and Machine Intelligence More from this journal
- Volume:
- 42
- Issue:
- 1
- Pages:
- 192-202
- Publication date:
- 2018-12-07
- Acceptance date:
- 2018-04-12
- DOI:
- EISSN:
-
1939-3539
- ISSN:
-
0162-8828
- Language:
-
English
- Keywords:
- Pubs id:
-
1078668
- Local pid:
-
pubs:1078668
- Deposit date:
-
2020-06-26
Terms of use
- Copyright holder:
- IEEE
- Copyright date:
- 2018
- Rights statement:
- © 2018 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission
- Notes:
- This is the accepted manuscript version of the article. The final version is available from IEEE at: https://doi.org/10.1109/TPAMI.2018.2885516
If you are the owner of this record, you can report an update to it here: Report update to this record