{"id":596,"date":"2019-04-22T14:57:38","date_gmt":"2019-04-22T13:57:38","guid":{"rendered":"http:\/\/pageperso.math.univ-toulouse.fr\/gfort\/?page_id=596"},"modified":"2023-07-31T15:25:14","modified_gmt":"2023-07-31T14:25:14","slug":"cc","status":"publish","type":"page","link":"https:\/\/perso.math.univ-toulouse.fr\/gfort\/project\/cc\/","title":{"rendered":"SDwithMI"},"content":{"rendered":"<p style=\"text-align: center\"><span style=\"font-size: 10pt\"><span style=\"font-size: 12pt\">Convergence of <strong>S<\/strong>tochastic <strong>D<\/strong>escent Algorithms <strong>with<\/strong> <strong>M<\/strong>arkovian <strong>I<\/strong>nputs<\/span><br \/>\n<\/span><\/p>\n<p><span style=\"font-size: 10pt\">Project funded by the Labex CIMI<\/span><\/p>\n<p style=\"text-align: justify\"><span style=\"font-size: 12pt\"><strong>Topic<\/strong>: Convergence of Stochastic Descent-based algorithms with Markovian inputs for non-smooth and convex optimization :<\/span><\/p>\n<ol style=\"text-align: justify\">\n<li><span style=\"font-size: 12pt\">Convergence of perturbed iterative algorithms, for convex composite optimization<\/span><\/li>\n<li><span style=\"font-size: 12pt\">Acceleration methods<\/span><\/li>\n<li><span style=\"font-size: 12pt\">Design and Convergence of Penalized Stochastic Approximation EM algorithms<\/span><\/li>\n<li><span style=\"font-size: 12pt\">Iterative algorithms for Quantile and Superquantile estimations.<\/span><\/li>\n<\/ol>\n<p style=\"text-align: justify\"><span style=\"font-size: 12pt\"><strong>P.I.<\/strong>: Gersende Fort<\/span><\/p>\n<p style=\"text-align: justify\"><span style=\"font-size: 12pt\"><strong>When<\/strong>: from January 2018 to December 2019<\/span><\/p>\n<p style=\"text-align: justify\"><span style=\"font-size: 12pt\"><strong>Local participants<\/strong>:<\/span><\/p>\n<ul style=\"text-align: justify\">\n<li><span style=\"font-size: 12pt\">Nicolas <a href=\"http:\/\/dobigeon.perso.enseeiht.fr\/\">Dobigeon<\/a> (IRIT)<\/span><\/li>\n<li><span style=\"font-size: 12pt\">Charles <a href=\"https:\/\/perso.math.univ-toulouse.fr\/cdossal\/\">Dossal<\/a> (IMT)<\/span><\/li>\n<li><span style=\"font-size: 12pt\">C\u00e9dric <a href=\"https:\/\/www.irit.fr\/~Cedric.Fevotte\/\">F\u00e9votte<\/a> (IRIT)<\/span><\/li>\n<li><span style=\"font-size: 12pt\">Gersende Fort (IMT)<\/span><\/li>\n<li><span style=\"font-size: 12pt\">S\u00e9bastien <a href=\"https:\/\/www.tse-fr.eu\/fr\/people\/sebastien-gadat\">Gadat<\/a> (TSE-R)<\/span><\/li>\n<li><span style=\"font-size: 12pt\">Aur\u00e9lien <a href=\"https:\/\/www.math.univ-toulouse.fr\/~agarivie\/?q=node\/34\">Garivier<\/a> (IMT puis ENS Lyon)<\/span><\/li>\n<li><span style=\"font-size: 12pt\">Laurent <a href=\"http:\/\/laurent.risser.free.fr\/menuEng.html\">Risser<\/a> (IMT)<\/span><\/li>\n<\/ul>\n<p style=\"text-align: justify\"><span style=\"font-size: 12pt\"><strong>External favouref partners:<\/strong><\/span><\/p>\n<ul style=\"text-align: justify\">\n<li><span style=\"font-size: 12pt\">Jean-Fran\u00e7ois <a href=\"https:\/\/www.math.u-bordeaux.fr\/~jaujol\/index.html\">Aujol<\/a> (IMB)<\/span><\/li>\n<li><span style=\"font-size: 12pt\">Emmanuel <a href=\"http:\/\/www.cmap.polytechnique.fr\/~gobet\/\">Gobet<\/a> (CMAP)<\/span><\/li>\n<li><span style=\"font-size: 12pt\">Anatoli <a href=\"https:\/\/ljk.imag.fr\/membres\/Anatoli.Iouditski\/\">Juditski<\/a> (LJK)<\/span><\/li>\n<li><span style=\"font-size: 12pt\">Eric Moulines (CMAP)<\/span><\/li>\n<li><span style=\"font-size: 12pt\">Adeline <a href=\"http:\/\/adeline.e-samson.org\/fr+en\/\">Samson<\/a> (LJK)<\/span><\/li>\n<\/ul>\n<p style=\"text-align: justify\"><span style=\"font-size: 12pt\"><strong>Scientific production:<\/strong><\/span><\/p>\n<p style=\"padding-left: 30px;text-align: justify\"><span style=\"font-size: 12pt\"><strong>Papers<\/strong><\/span><\/p>\n<ol style=\"text-align: justify\">\n<li style=\"padding-left: 30px;text-align: justify\"><span style=\"font-size: 12pt\">G. Fort, E. Ollier and A. Leclerc-Samson. Stochastic Proximal Gradient Algorithms for Penalized Mixed Models. <em>Statistics and Computing, 29(2):231-253, 2019.<\/em><\/span><\/li>\n<li style=\"padding-left: 30px;text-align: justify\"><span style=\"font-size: 12pt\">G. Fort, L. Risser, Y. Atchad\u00e9 and E. Moulines. Stochastic FISTA algorithms: so fast ? <em>Proceedings of the IEEE Statistical Signal Processing workshop, pp.796-800, June 2018.<\/em><\/span><\/li>\n<li style=\"padding-left: 30px;text-align: justify\"><span style=\"font-size: 12pt\">S. Crepey, G. Fort, E. Gobet and U. Stazhynski<small>. <\/small><a href=\"https:\/\/www.math.univ-toulouse.fr\/%7Egfort\/Slides\/Gretsi19.pdf\">Quantification d&#8217;incertitude pour l&#8217;Approximation Stochastique<\/a>. <em>Accept\u00e9, Actes de conf\u00e9rence du GRETSI 2019.<br \/>\n<\/em><\/span><\/li>\n<li style=\"padding-left: 30px;text-align: justify\"><span style=\"font-size: 12pt\">S. Crepey, G. Fort, E. Gobet and U. Stazhynski. Uncertainty quantification for Stochastic Approximation limits using Chaos Expansion.<em> Accepted for publication in SIAM-ASA Journal on Uncertainty Quantification, 2020.<br \/>\n<\/em><\/span><\/li>\n<li style=\"padding-left: 30px;text-align: justify\"><span style=\"font-size: 12pt\">C. Dossal &#8211; xxx<\/span><\/li>\n<li style=\"padding-left: 30px;text-align: justify\"><span style=\"font-size: 12pt\">C. Dossal &#8211; xxx<\/span><\/li>\n<li style=\"padding-left: 30px;text-align: justify\"><span style=\"font-size: 12pt\">L. Risser &#8211; xxx<\/span><\/li>\n<\/ol>\n<p style=\"padding-left: 30px;text-align: justify\"><span style=\"font-size: 12pt\"><strong>Talks<\/strong><\/span><\/p>\n<ol style=\"text-align: justify\">\n<li style=\"padding-left: 30px\"><span style=\"font-size: 12pt\">By G. Fort. Conference IEEE Statistical Signal Processing; Freiburg, Germany; June 2018.<\/span><\/li>\n<li style=\"padding-left: 30px\"><span style=\"font-size: 12pt\">By C. Dossal. 1st Workshop &#8220;Advances in nonsmooth analysis and optimization&#8221;, Erice, Italy; June 2019.<\/span><\/li>\n<li style=\"padding-left: 30px\"><span style=\"font-size: 12pt\">By G. Fort. Conf\u00e9rence francophone GRETSI, Lille; Ao\u00fbt 2019.<\/span><\/li>\n<li style=\"padding-left: 30px\"><span style=\"font-size: 12pt\">By G. Fort. PGMO days, December 2019.<em><br \/>\n<\/em><\/span><\/li>\n<li style=\"padding-left: 30px\">By G. Fort. Conference &#8220;Optimization for Machine Learning&#8221;, CIRM, Mars 2020.<\/li>\n<\/ol>\n<p style=\"padding-left: 30px;text-align: justify\"><span style=\"font-size: 12pt\"><strong>Workshop<\/strong><\/span><\/p>\n<p style=\"padding-left: 30px;text-align: left\"><span style=\"font-size: 12pt\">Co-organization of the semester &#8220;Optimization&#8221; funded by the Labex CIMI : a <a href=\"http:\/\/cimi.univ-toulouse.fr\/optimisation\/fr\/workshop-optimisation-aspects-fondamentaux-et-exploitation-de-la-structure\">first workshop<\/a> in June 2018 on &#8220;Aspects fondamentaux et Exploitation de la structure&#8221; with C. Dossal and S. Gadat as co-organizers ; and a <a href=\"http:\/\/www.cimi.univ-toulouse.fr\/optimisation\/en\/workshop-optimization-and-machine-learning\">second workshop<\/a> on &#8220;Optimization and Learning&#8221; co-organized by G. Fort, S. Gadat, A. Garivier, L. Risser and C. F\u00e9votte.<\/span><\/p>\n<p style=\"padding-left: 30px;text-align: left\"><strong>Stage<\/strong><\/p>\n<ul>\n<li style=\"padding-left: 30px;text-align: left\">M2\u00a0 ( see C. Dossal)<\/li>\n<\/ul>\n<p style=\"text-align: left\"><strong><span style=\"font-size: 12pt\">And after ?<\/span> <\/strong><\/p>\n<p style=\"padding-left: 30px;text-align: justify\"><span style=\"font-size: 12pt\">These CIMI fundings were a cornerstone for its members, in order to apply to other projects funded by national grants:<\/span><\/p>\n<ul>\n<li style=\"padding-left: 30px;text-align: justify\"><span style=\"font-size: 12pt\">C. Dossal, G. Fort and S. Gadat are part of a project funded by the french National Research Agency (ANR), starting in Autumn 2019.\u00a0 The P.I. is S. Gadat. It involves researchers from Bordeaux (IMB) and Toulouse (IMT, TSE-R).<\/span><\/li>\n<li style=\"padding-left: 30px;text-align: justify\"><span style=\"font-size: 12pt\">G. Fort, S. Gadat and L. Risser are part of a project funded by the Fondation Simone and Cino Del Duca, starting in January 2020. The P.I. is G. Fort<\/span><\/li>\n<li style=\"padding-left: 30px;text-align: justify\"><span style=\"font-size: 12pt\">S. Dobigeon, C. F\u00e9votte, and L. Risser are members of a national program for Artificial Intelligence, &#8220;Artificial and Natural Intelligence Toulouse Institute (ANITI)&#8221;, starting in Autumn 2019.<\/span><\/li>\n<\/ul>\n<p style=\"padding-left: 30px;text-align: justify\"><span style=\"font-size: 12pt\">\u00a0<\/span><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Convergence of Stochastic Descent Algorithms with Markovian Inputs Project funded by the Labex CIMI Topic: Convergence of Stochastic Descent-based algorithms with Markovian inputs for non-smooth and convex optimization : Convergence of perturbed iterative algorithms, for convex composite optimization Acceleration methods Design and Convergence of Penalized Stochastic Approximation EM algorithms Iterative algorithms for Quantile and Superquantile [&hellip;]<\/p>\n","protected":false},"author":194,"featured_media":0,"parent":88,"menu_order":5,"comment_status":"closed","ping_status":"open","template":"full-width-page.php","meta":{"footnotes":""},"class_list":["post-596","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/perso.math.univ-toulouse.fr\/gfort\/wp-json\/wp\/v2\/pages\/596","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/perso.math.univ-toulouse.fr\/gfort\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/perso.math.univ-toulouse.fr\/gfort\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/perso.math.univ-toulouse.fr\/gfort\/wp-json\/wp\/v2\/users\/194"}],"replies":[{"embeddable":true,"href":"https:\/\/perso.math.univ-toulouse.fr\/gfort\/wp-json\/wp\/v2\/comments?post=596"}],"version-history":[{"count":22,"href":"https:\/\/perso.math.univ-toulouse.fr\/gfort\/wp-json\/wp\/v2\/pages\/596\/revisions"}],"predecessor-version":[{"id":5416,"href":"https:\/\/perso.math.univ-toulouse.fr\/gfort\/wp-json\/wp\/v2\/pages\/596\/revisions\/5416"}],"up":[{"embeddable":true,"href":"https:\/\/perso.math.univ-toulouse.fr\/gfort\/wp-json\/wp\/v2\/pages\/88"}],"wp:attachment":[{"href":"https:\/\/perso.math.univ-toulouse.fr\/gfort\/wp-json\/wp\/v2\/media?parent=596"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}