@inproceedings{chretien2019revisiting,
title={Revisiting clustering as matrix factorisation on the {Stiefel} manifold},
author={Chr{\'e}tien, St{\'e}phane and Guedj, Benjamin},
year={2020},
editor="Nicosia, Giuseppe
and Ojha, Varun
and La Malfa, Emanuele
and Jansen, Giorgio
and Sciacca, Vincenzo
and Pardalos, Panos
and Giuffrida, Giovanni
and Umeton, Renato",
publisher="Springer International Publishing",
pages="1--12",
abstract = "This paper studies clustering for possibly high dimensional data (e.g. images, time series, gene expression data, and many other settings), and rephrase it as low rank matrix estimation in the PAC-Bayesian framework. Our approach leverages the well known Burer-Monteiro factorisation strategy from large scale optimisation, in the context of low rank estimation. Moreover, our Burer-Monteiro factors are shown to lie on a Stiefel manifold. We propose a new generalized Bayesian estimator for this problem and prove novel prediction bounds for clustering. We also devise a componentwise Langevin sampler on the Stiefel manifold to compute this estimator.",
booktitle="LOD -- The Sixth International Conference on Machine Learning, Optimization, and Data Science",
isbn="978-3-030-64583-0",
url = "https://link.springer.com/chapter/10.1007%2F978-3-030-64583-0_1",
url_arXiv = "https://arxiv.org/abs/1903.04479",
url_PDF = "https://arxiv.org/pdf/1903.04479.pdf",
url_Video = "https://youtu.be/Gz2euWW8kyA",
DOI = "10.1007/978-3-030-64583-0_1",
keywords={mine}
}

{"_id":"kvTvLibXWWyz6PYf5","bibbaseid":"chrtien-guedj-revisitingclusteringasmatrixfactorisationonthestiefelmanifold-2020","author_short":["Chrétien, S.","Guedj, B."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Revisiting clustering as matrix factorisation on the Stiefel manifold","author":[{"propositions":[],"lastnames":["Chrétien"],"firstnames":["Stéphane"],"suffixes":[]},{"propositions":[],"lastnames":["Guedj"],"firstnames":["Benjamin"],"suffixes":[]}],"year":"2020","editor":[{"propositions":[],"lastnames":["Nicosia"],"firstnames":["Giuseppe"],"suffixes":[]},{"propositions":[],"lastnames":["Ojha"],"firstnames":["Varun"],"suffixes":[]},{"propositions":[],"lastnames":["La","Malfa"],"firstnames":["Emanuele"],"suffixes":[]},{"propositions":[],"lastnames":["Jansen"],"firstnames":["Giorgio"],"suffixes":[]},{"propositions":[],"lastnames":["Sciacca"],"firstnames":["Vincenzo"],"suffixes":[]},{"propositions":[],"lastnames":["Pardalos"],"firstnames":["Panos"],"suffixes":[]},{"propositions":[],"lastnames":["Giuffrida"],"firstnames":["Giovanni"],"suffixes":[]},{"propositions":[],"lastnames":["Umeton"],"firstnames":["Renato"],"suffixes":[]}],"publisher":"Springer International Publishing","pages":"1–12","abstract":"This paper studies clustering for possibly high dimensional data (e.g. images, time series, gene expression data, and many other settings), and rephrase it as low rank matrix estimation in the PAC-Bayesian framework. Our approach leverages the well known Burer-Monteiro factorisation strategy from large scale optimisation, in the context of low rank estimation. Moreover, our Burer-Monteiro factors are shown to lie on a Stiefel manifold. We propose a new generalized Bayesian estimator for this problem and prove novel prediction bounds for clustering. We also devise a componentwise Langevin sampler on the Stiefel manifold to compute this estimator.","booktitle":"LOD – The Sixth International Conference on Machine Learning, Optimization, and Data Science","isbn":"978-3-030-64583-0","url":"https://link.springer.com/chapter/10.1007%2F978-3-030-64583-0_1","url_arxiv":"https://arxiv.org/abs/1903.04479","url_pdf":"https://arxiv.org/pdf/1903.04479.pdf","url_video":"https://youtu.be/Gz2euWW8kyA","doi":"10.1007/978-3-030-64583-0_1","keywords":"mine","bibtex":"@inproceedings{chretien2019revisiting,\ntitle={Revisiting clustering as matrix factorisation on the {Stiefel} manifold},\nauthor={Chr{\\'e}tien, St{\\'e}phane and Guedj, Benjamin},\nyear={2020},\neditor=\"Nicosia, Giuseppe\nand Ojha, Varun\nand La Malfa, Emanuele\nand Jansen, Giorgio\nand Sciacca, Vincenzo\nand Pardalos, Panos\nand Giuffrida, Giovanni\nand Umeton, Renato\",\npublisher=\"Springer International Publishing\",\npages=\"1--12\",\nabstract = \"This paper studies clustering for possibly high dimensional data (e.g. images, time series, gene expression data, and many other settings), and rephrase it as low rank matrix estimation in the PAC-Bayesian framework. Our approach leverages the well known Burer-Monteiro factorisation strategy from large scale optimisation, in the context of low rank estimation. Moreover, our Burer-Monteiro factors are shown to lie on a Stiefel manifold. We propose a new generalized Bayesian estimator for this problem and prove novel prediction bounds for clustering. We also devise a componentwise Langevin sampler on the Stiefel manifold to compute this estimator.\",\nbooktitle=\"LOD -- The Sixth International Conference on Machine Learning, Optimization, and Data Science\",\nisbn=\"978-3-030-64583-0\",\nurl = \"https://link.springer.com/chapter/10.1007%2F978-3-030-64583-0_1\",\nurl_arXiv = \"https://arxiv.org/abs/1903.04479\",\nurl_PDF = \"https://arxiv.org/pdf/1903.04479.pdf\",\nurl_Video = \"https://youtu.be/Gz2euWW8kyA\",\nDOI = \"10.1007/978-3-030-64583-0_1\",\nkeywords={mine}\n}\n\n","author_short":["Chrétien, S.","Guedj, B."],"editor_short":["Nicosia, G.","Ojha, V.","La Malfa, E.","Jansen, G.","Sciacca, V.","Pardalos, P.","Giuffrida, G.","Umeton, R."],"key":"chretien2019revisiting","id":"chretien2019revisiting","bibbaseid":"chrtien-guedj-revisitingclusteringasmatrixfactorisationonthestiefelmanifold-2020","role":"author","urls":{"Paper":"https://link.springer.com/chapter/10.1007%2F978-3-030-64583-0_1"," arxiv":"https://arxiv.org/abs/1903.04479"," pdf":"https://arxiv.org/pdf/1903.04479.pdf"," video":"https://youtu.be/Gz2euWW8kyA"},"keyword":["mine"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"inproceedings","biburl":"https://bguedj.github.io/files/bguedj-publications.bib","dataSources":["suE7RgYeZEnSYr5Fy"],"keywords":["mine"],"search_terms":["revisiting","clustering","matrix","factorisation","stiefel","manifold","chrétien","guedj"],"title":"Revisiting clustering as matrix factorisation on the Stiefel manifold","year":2020}