{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T23:20:54Z","timestamp":1770333654051,"version":"3.49.0"},"reference-count":14,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2021,4,12]],"date-time":"2021-04-12T00:00:00Z","timestamp":1618185600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,4,12]],"date-time":"2021-04-12T00:00:00Z","timestamp":1618185600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100004359","name":"Vetenskapsr\u00e5det","doi-asserted-by":"publisher","award":["2016-03346, 2017-2020"],"award-info":[{"award-number":["2016-03346, 2017-2020"]}],"id":[{"id":"10.13039\/501100004359","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014440","name":"Ministerio de Ciencia, Innovaci\u00f3n y Universidades","doi-asserted-by":"publisher","award":["TIN2017-87211-R"],"award-info":[{"award-number":["TIN2017-87211-R"]}],"id":[{"id":"10.13039\/100014440","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004063","name":"Knut och Alice Wallenbergs Stiftelse","doi-asserted-by":"publisher","award":["WASP"],"award-info":[{"award-number":["WASP"]}],"id":[{"id":"10.13039\/501100004063","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Prog Artif Intell"],"published-print":{"date-parts":[[2021,9]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Machine and statistical learning is about constructing models from data. Data is usually understood as a set of records, a database. Nevertheless, databases are not static but change over time. We can understand this as follows: there is a space of possible databases and a database during its lifetime transits this space. Therefore, we may consider transitions between databases, and the database space. NoSQL databases also fit with this representation. In addition, when we learn models from databases, we can also consider the space of models. Naturally, there are relationships between the space of data and the space of models. Any transition in the space of data may correspond to a transition in the space of models. We argue that a better understanding of the space of data and the space of models, as well as the relationships between these two spaces is basic for machine and statistical learning. The relationship between these two spaces can be exploited in several contexts as, e.g., in model selection and data privacy. We consider that this relationship between spaces is also fundamental to understand generalization and overfitting. In this paper, we develop these ideas. Then, we consider a distance on the space of models based on a distance on the space of data. More particularly, we consider distance distribution functions and probabilistic metric spaces on the space of data and the space of models. Our modelization of changes in databases is based on Markov chains and transition matrices. This modelization is used in the definition of distances. We provide examples of our definitions.<\/jats:p>","DOI":"10.1007\/s13748-021-00242-6","type":"journal-article","created":{"date-parts":[[2021,4,12]],"date-time":"2021-04-12T20:03:09Z","timestamp":1618257789000},"page":"321-332","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["The space of models in machine learning: using Markov chains to model transitions"],"prefix":"10.1007","volume":"10","author":[{"given":"Vicen\u00e7","family":"Torra","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mariam","family":"Taha","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guillermo","family":"Navarro-Arribas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,4,12]]},"reference":[{"key":"242_CR1","doi-asserted-by":"publisher","DOI":"10.1142\/9789812774200","volume-title":"Associative Functions: Triangular Norms and Copulas","author":"C Alsina","year":"2006","unstructured":"Alsina, C., Frank, M.J., Schweizer, B.: Associative Functions: Triangular Norms and Copulas. World Scientific, Singapore (2006)"},{"key":"242_CR2","volume-title":"Stochastic Processes","author":"JL Doob","year":"1953","unstructured":"Doob, J.L.: Stochastic Processes. Wiley, Hoboken (1953)"},{"key":"242_CR3","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1007\/s002360050075","volume":"34","author":"T Eiter","year":"1997","unstructured":"Eiter, T., Mannila, H.: Distance measures for point sets and their computation. Acta Informatica 34, 109\u2013133 (1997)","journal-title":"Acta Informatica"},{"key":"242_CR4","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1017\/S1446788700030391","volume":"46","author":"DC Kent","year":"1989","unstructured":"Kent, D.C., Richardson, G.D.: Ordered probabilistic metric spaces. J. Austral. Math. Soc. 46, 88\u201399 (1989)","journal-title":"J. Austral. Math. Soc."},{"key":"242_CR5","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1007\/BF01835647","volume":"15","author":"PS Marcus","year":"1977","unstructured":"Marcus, P.S.: Probabilistic metric spaces constructed from stationary Markov chains. Aequationes Mathematica 15, 169\u2013171 (1977)","journal-title":"Aequationes Mathematica"},{"key":"242_CR6","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1007\/BF00533323","volume":"35","author":"R Moynihan","year":"1976","unstructured":"Moynihan, R.: Probabilistic metric spaces induced by Markov chains. Z. Wahrscheinlichkeitstheorie. Gebiete 35, 177\u2013187 (1976)","journal-title":"Z. Wahrscheinlichkeitstheorie. Gebiete"},{"key":"242_CR7","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-13-0659-4","volume-title":"Understanding Markov Chains","author":"N Privault","year":"2018","unstructured":"Privault, N.: Understanding Markov Chains. Springer, Newyork (2018)"},{"issue":"6","key":"242_CR8","doi-asserted-by":"publisher","first-page":"1010","DOI":"10.1109\/69.971193","volume":"13","author":"P Samarati","year":"2001","unstructured":"Samarati, P.: Protecting respondents identities in microdata release. IEEE Trans. Knowl. Data Eng. 13(6), 1010\u20131027 (2001)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"242_CR9","volume-title":"Probabilistic Metric Spaces","author":"B Schweizer","year":"1983","unstructured":"Schweizer, B., Sklar, A.: Probabilistic Metric Spaces. Elsevier, Amsterdam (1983)"},{"key":"242_CR10","first-page":"1","volume":"2018","author":"N Senavirathne","year":"2018","unstructured":"Senavirathne, N., Torra, V.: Approximating robust linear regression with an integral privacy guarantee. Proc. PST 2018, 1\u201310 (2018)","journal-title":"Proc. PST"},{"key":"242_CR11","first-page":"22","volume":"2019","author":"N Senavirathne","year":"2019","unstructured":"Senavirathne, N., Torra, V.: Integral privacy compliant statistics computation. Proc DPM\/CBT- ESORICS 2019, 22\u201338 (2019)","journal-title":"Proc DPM\/CBT- ESORICS"},{"key":"242_CR12","unstructured":"Shokri, R., Stronati, M., Song, C., Shmatikov, V.: Membership inference attacks against machine learning models. Proc. IEEE Symposium on Security and Privacy. (2017). arXiv:1610.05820"},{"key":"242_CR13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-57358-8","volume-title":"Data Privacy: Foundations, New Developments and the Big Data Challenge","author":"V Torra","year":"2017","unstructured":"Torra, V.: Data Privacy: Foundations, New Developments and the Big Data Challenge. Springer, Newyork (2017)"},{"key":"242_CR14","first-page":"422","volume":"11025","author":"V Torra","year":"2018","unstructured":"Torra, V., Navarro-Arribas, G.: Probabilistic metric spaces for privacy by design machine learning algorithms: modeling database changes, Proc. DPM 2018\/CBT 2018. LNCS 11025, 422\u2013430 (2018)","journal-title":"LNCS"}],"container-title":["Progress in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13748-021-00242-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13748-021-00242-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13748-021-00242-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,8,12]],"date-time":"2021-08-12T11:13:37Z","timestamp":1628766817000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13748-021-00242-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,12]]},"references-count":14,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2021,9]]}},"alternative-id":["242"],"URL":"https:\/\/doi.org\/10.1007\/s13748-021-00242-6","relation":{},"ISSN":["2192-6352","2192-6360"],"issn-type":[{"value":"2192-6352","type":"print"},{"value":"2192-6360","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4,12]]},"assertion":[{"value":"4 April 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 March 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 April 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}