Kernel Method for Persistence Diagrams via Kernel Embedding and Weight Factor. Kusano, G., Fukumizu, K., & Hiraoka, Y. ![Kernel Method for Persistence Diagrams via Kernel Embedding and Weight Factor [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper abstract bibtex Topological data analysis is an emerging mathematical concept for characterizing shapes in multi-scale data. In this field, persistence diagrams are widely used as a descriptor of the input data, and can distinguish robust and noisy topological properties. Nowadays, it is highly desired to develop a statistical framework on persistence diagrams to deal with practical data. This paper proposes a kernel method on persistence diagrams. A theoretical contribution of our method is that the proposed kernel allows one to control the effect of persistence, and, if necessary, noisy topological properties can be discounted in data analysis. Furthermore, the method provides a fast approximation technique. The method is applied into several problems including practical data in physics, and the results show the advantage compared to the existing kernel method on persistence diagrams.
@article{kusanoKernelMethodPersistence2017,
archivePrefix = {arXiv},
eprinttype = {arxiv},
eprint = {1706.03472},
primaryClass = {physics, stat},
title = {Kernel Method for Persistence Diagrams via Kernel Embedding and Weight Factor},
url = {http://arxiv.org/abs/1706.03472},
abstract = {Topological data analysis is an emerging mathematical concept for characterizing shapes in multi-scale data. In this field, persistence diagrams are widely used as a descriptor of the input data, and can distinguish robust and noisy topological properties. Nowadays, it is highly desired to develop a statistical framework on persistence diagrams to deal with practical data. This paper proposes a kernel method on persistence diagrams. A theoretical contribution of our method is that the proposed kernel allows one to control the effect of persistence, and, if necessary, noisy topological properties can be discounted in data analysis. Furthermore, the method provides a fast approximation technique. The method is applied into several problems including practical data in physics, and the results show the advantage compared to the existing kernel method on persistence diagrams.},
urldate = {2018-06-12},
date = {2017-06-12},
keywords = {Statistics - Machine Learning,Mathematics - Algebraic Topology,Physics - Data Analysis; Statistics and Probability},
author = {Kusano, Genki and Fukumizu, Kenji and Hiraoka, Yasuaki},
file = {/home/dimitri/Nextcloud/Zotero/storage/ISLEIEE9/Kusano et al. - 2017 - Kernel method for persistence diagrams via kernel .pdf;/home/dimitri/Nextcloud/Zotero/storage/6FIXWZVF/1706.html}
}
Downloads: 0
{"_id":"CYBd4Emjgznzku8b6","bibbaseid":"kusano-fukumizu-hiraoka-kernelmethodforpersistencediagramsviakernelembeddingandweightfactor","authorIDs":[],"author_short":["Kusano, G.","Fukumizu, K.","Hiraoka, Y."],"bibdata":{"bibtype":"article","type":"article","archiveprefix":"arXiv","eprinttype":"arxiv","eprint":"1706.03472","primaryclass":"physics, stat","title":"Kernel Method for Persistence Diagrams via Kernel Embedding and Weight Factor","url":"http://arxiv.org/abs/1706.03472","abstract":"Topological data analysis is an emerging mathematical concept for characterizing shapes in multi-scale data. In this field, persistence diagrams are widely used as a descriptor of the input data, and can distinguish robust and noisy topological properties. Nowadays, it is highly desired to develop a statistical framework on persistence diagrams to deal with practical data. This paper proposes a kernel method on persistence diagrams. A theoretical contribution of our method is that the proposed kernel allows one to control the effect of persistence, and, if necessary, noisy topological properties can be discounted in data analysis. Furthermore, the method provides a fast approximation technique. The method is applied into several problems including practical data in physics, and the results show the advantage compared to the existing kernel method on persistence diagrams.","urldate":"2018-06-12","date":"2017-06-12","keywords":"Statistics - Machine Learning,Mathematics - Algebraic Topology,Physics - Data Analysis; Statistics and Probability","author":[{"propositions":[],"lastnames":["Kusano"],"firstnames":["Genki"],"suffixes":[]},{"propositions":[],"lastnames":["Fukumizu"],"firstnames":["Kenji"],"suffixes":[]},{"propositions":[],"lastnames":["Hiraoka"],"firstnames":["Yasuaki"],"suffixes":[]}],"file":"/home/dimitri/Nextcloud/Zotero/storage/ISLEIEE9/Kusano et al. - 2017 - Kernel method for persistence diagrams via kernel .pdf;/home/dimitri/Nextcloud/Zotero/storage/6FIXWZVF/1706.html","bibtex":"@article{kusanoKernelMethodPersistence2017,\n archivePrefix = {arXiv},\n eprinttype = {arxiv},\n eprint = {1706.03472},\n primaryClass = {physics, stat},\n title = {Kernel Method for Persistence Diagrams via Kernel Embedding and Weight Factor},\n url = {http://arxiv.org/abs/1706.03472},\n abstract = {Topological data analysis is an emerging mathematical concept for characterizing shapes in multi-scale data. In this field, persistence diagrams are widely used as a descriptor of the input data, and can distinguish robust and noisy topological properties. Nowadays, it is highly desired to develop a statistical framework on persistence diagrams to deal with practical data. This paper proposes a kernel method on persistence diagrams. A theoretical contribution of our method is that the proposed kernel allows one to control the effect of persistence, and, if necessary, noisy topological properties can be discounted in data analysis. Furthermore, the method provides a fast approximation technique. The method is applied into several problems including practical data in physics, and the results show the advantage compared to the existing kernel method on persistence diagrams.},\n urldate = {2018-06-12},\n date = {2017-06-12},\n keywords = {Statistics - Machine Learning,Mathematics - Algebraic Topology,Physics - Data Analysis; Statistics and Probability},\n author = {Kusano, Genki and Fukumizu, Kenji and Hiraoka, Yasuaki},\n file = {/home/dimitri/Nextcloud/Zotero/storage/ISLEIEE9/Kusano et al. - 2017 - Kernel method for persistence diagrams via kernel .pdf;/home/dimitri/Nextcloud/Zotero/storage/6FIXWZVF/1706.html}\n}\n\n","author_short":["Kusano, G.","Fukumizu, K.","Hiraoka, Y."],"key":"kusanoKernelMethodPersistence2017","id":"kusanoKernelMethodPersistence2017","bibbaseid":"kusano-fukumizu-hiraoka-kernelmethodforpersistencediagramsviakernelembeddingandweightfactor","role":"author","urls":{"Paper":"http://arxiv.org/abs/1706.03472"},"keyword":["Statistics - Machine Learning","Mathematics - Algebraic Topology","Physics - Data Analysis; Statistics and Probability"],"downloads":0},"bibtype":"article","biburl":"https://raw.githubusercontent.com/dlozeve/newblog/master/bib/all.bib","creationDate":"2020-01-08T20:39:39.151Z","downloads":0,"keywords":["statistics - machine learning","mathematics - algebraic topology","physics - data analysis; statistics and probability"],"search_terms":["kernel","method","persistence","diagrams","via","kernel","embedding","weight","factor","kusano","fukumizu","hiraoka"],"title":"Kernel Method for Persistence Diagrams via Kernel Embedding and Weight Factor","year":null,"dataSources":["3XqdvqRE7zuX4cm8m"]}