{"id":280,"date":"2020-09-18T08:12:15","date_gmt":"2020-09-18T07:12:15","guid":{"rendered":"https:\/\/yanntraonmilin.wordpress.com\/?page_id=280"},"modified":"2025-01-23T08:21:28","modified_gmt":"2025-01-23T08:21:28","slug":"news","status":"publish","type":"page","link":"https:\/\/yanntraonmilin.perso.math.cnrs.fr\/","title":{"rendered":"News"},"content":{"rendered":"\n<div class=\"wp-block-group alignfull has-background-background-color has-background\"><div class=\"wp-block-group__inner-container is-layout-flow wp-block-group-is-layout-flow\">\n<div class=\"wp-block-jetpack-layout-grid alignfull column1-desktop-grid__span-9 column1-desktop-grid__row-1 column2-desktop-grid__span-3 column2-desktop-grid__start-10 column2-desktop-grid__row-1 column1-tablet-grid__span-5 column1-tablet-grid__row-1 column2-tablet-grid__span-3 column2-tablet-grid__start-6 column2-tablet-grid__row-1 column1-mobile-grid__span-4 column1-mobile-grid__row-1 column2-mobile-grid__span-4 column2-mobile-grid__row-2\">\n<div class=\"wp-block-jetpack-layout-grid-column wp-block-jetpack-layout-grid__padding-large\">\n<div class=\"wp-block-query is-layout-flow wp-block-query-is-layout-flow\"><ul class=\"columns-3 wp-block-post-template is-layout-grid wp-container-core-post-template-is-layout-2fc57c17 wp-block-post-template-is-layout-grid\"><li class=\"wp-block-post post-632 post type-post status-publish format-standard hentry category-uncategorized\">\n\n<div class=\"wp-block-group\" style=\"padding-top:30px;padding-right:30px;padding-bottom:30px;padding-left:30px\"><div class=\"wp-block-group__inner-container is-layout-flow wp-block-group-is-layout-flow\"><h2 class=\"wp-block-post-title\"><a href=\"https:\/\/yanntraonmilin.perso.math.cnrs.fr\/?p=632\" target=\"_self\" >Best paper award ! (highlight talk)<\/a><\/h2>\n\n<div class=\"wp-block-post-excerpt\"><p class=\"wp-block-post-excerpt__excerpt\">Our paper From sparse recovery to plug-and-play priors, understanding trade-offs for stable recovery with generalized projected gradient descent, (A. Joundi, Y. Traonmilin, J.-F. Aujol) won one of the best papers award (highlight talk) of the Conference on Parsimony and Learning,\u00a0 2026. Congrats everyone ! <\/p><\/div>\n\n<div class=\"wp-block-post-date\"><time datetime=\"2026-02-23T08:23:53+00:00\">February 23, 2026<\/time><\/div><\/div><\/div>\n\n<\/li><li class=\"wp-block-post post-625 post type-post status-publish format-standard hentry category-uncategorized\">\n\n<div class=\"wp-block-group\" style=\"padding-top:30px;padding-right:30px;padding-bottom:30px;padding-left:30px\"><div class=\"wp-block-group__inner-container is-layout-flow wp-block-group-is-layout-flow\"><h2 class=\"wp-block-post-title\"><a href=\"https:\/\/yanntraonmilin.perso.math.cnrs.fr\/?p=625\" target=\"_self\" >3 Papers accepted !<\/a><\/h2>\n\n<div class=\"wp-block-post-excerpt\"><p class=\"wp-block-post-excerpt__excerpt\">We just had the following papers accepted ! Congrats to everyone especially Phd students (S. Houache and A; Joundi) From sparse recovery to plug-and-play priors, understanding trade-offs for stable recovery with generalized projected gradient descent, A. Joundi, Y. Traonmilin, J.-F. Aujol, Accepted to Conference on Parsimony and Learning,\u00a0 2026. A Recovery Theory for Diffusion Priors:&hellip; <\/p><\/div>\n\n<div class=\"wp-block-post-date\"><time datetime=\"2026-01-22T14:52:04+00:00\">January 22, 2026<\/time><\/div><\/div><\/div>\n\n<\/li><li class=\"wp-block-post post-619 post type-post status-publish format-standard hentry category-paper\">\n\n<div class=\"wp-block-group\" style=\"padding-top:30px;padding-right:30px;padding-bottom:30px;padding-left:30px\"><div class=\"wp-block-group__inner-container is-layout-flow wp-block-group-is-layout-flow\"><h2 class=\"wp-block-post-title\"><a href=\"https:\/\/yanntraonmilin.perso.math.cnrs.fr\/?p=619\" target=\"_self\" >New preprint<\/a><\/h2>\n\n<div class=\"wp-block-post-excerpt\"><p class=\"wp-block-post-excerpt__excerpt\">We uploaded the preprint Stochastic Orthogonal Regularization for deep projective priors,\u00a0 A. Joundi, Y. Traonmilin, A. Newson, 2025. abstract: &#8220;Many crucial tasks of image processing and computer vision are formulated as inverse problems. Thus, it is of great importance to design fast and robust algorithms to solve these problems. In this paper, we focus on&hellip; <\/p><\/div>\n\n<div class=\"wp-block-post-date\"><time datetime=\"2025-12-09T15:35:39+00:00\">December 9, 2025<\/time><\/div><\/div><\/div>\n\n<\/li><li class=\"wp-block-post post-613 post type-post status-publish format-standard hentry category-paper\">\n\n<div class=\"wp-block-group\" style=\"padding-top:30px;padding-right:30px;padding-bottom:30px;padding-left:30px\"><div class=\"wp-block-group__inner-container is-layout-flow wp-block-group-is-layout-flow\"><h2 class=\"wp-block-post-title\"><a href=\"https:\/\/yanntraonmilin.perso.math.cnrs.fr\/?p=613\" target=\"_self\" >New preprint<\/a><\/h2>\n\n<div class=\"wp-block-post-excerpt\"><p class=\"wp-block-post-excerpt__excerpt\">We uploaded &#8220;On the impact of the parametrization of deep convolutional neural networks on post-training quantization&#8220;, S. Houache, J.-F. Aujol, Y.T. This paper introduces novel theoretical approximation bounds for the output of quantized neural networks, with a focus on convolutional neural networks (CNN). By considering layerwise parametrization and focusing on the quantization of weights, we&hellip; <\/p><\/div>\n\n<div class=\"wp-block-post-date\"><time datetime=\"2025-10-10T07:24:18+00:00\">October 10, 2025<\/time><\/div><\/div><\/div>\n\n<\/li><li class=\"wp-block-post post-604 post type-post status-publish format-standard hentry category-event category-students\">\n\n<div class=\"wp-block-group\" style=\"padding-top:30px;padding-right:30px;padding-bottom:30px;padding-left:30px\"><div class=\"wp-block-group__inner-container is-layout-flow wp-block-group-is-layout-flow\"><h2 class=\"wp-block-post-title\"><a href=\"https:\/\/yanntraonmilin.perso.math.cnrs.fr\/?p=604\" target=\"_self\" >New PhD<\/a><\/h2>\n\n<div class=\"wp-block-post-excerpt\"><p class=\"wp-block-post-excerpt__excerpt\">Congrats Dr Antoine Guennec who defended is PhD thesis yesterday on &#8220;Sparse models and deep priors for image decomposition into structure and texture&#8221;. He gave very nice contributions with modern methods on a challenging ill-posed problem. antoineguennec.perso.math.cnrs.fr <\/p><\/div>\n\n<div class=\"wp-block-post-date\"><time datetime=\"2025-07-22T08:54:39+00:00\">July 22, 2025<\/time><\/div><\/div><\/div>\n\n<\/li><li class=\"wp-block-post post-593 post type-post status-publish format-standard hentry category-talk\">\n\n<div class=\"wp-block-group\" style=\"padding-top:30px;padding-right:30px;padding-bottom:30px;padding-left:30px\"><div class=\"wp-block-group__inner-container is-layout-flow wp-block-group-is-layout-flow\"><h2 class=\"wp-block-post-title\"><a href=\"https:\/\/yanntraonmilin.perso.math.cnrs.fr\/?p=593\" target=\"_self\" >Talk at SMAI conference<\/a><\/h2>\n\n<div class=\"wp-block-post-excerpt\"><p class=\"wp-block-post-excerpt__excerpt\">I will be presenting my work on optimal low-dimensional recovery at SMAI 2025 (Thursday June 3rd). <\/p><\/div>\n\n<div class=\"wp-block-post-date\"><time datetime=\"2025-05-23T07:14:14+00:00\">May 23, 2025<\/time><\/div><\/div><\/div>\n\n<\/li><\/ul><\/div>\n<\/div>\n\n\n\n<div class=\"wp-block-jetpack-layout-grid-column wp-block-jetpack-layout-grid__padding-large\">\n<h5 class=\"wp-block-heading\" id=\"yann-traonmilin\">Yann Traonmilin <\/h5>\n\n\n\n<p>I am a CNRS researcher in the <a href=\"http:\/\/iop.math.u-bordeaux.fr\/?lang=fr\">IOP team<\/a> of the Institut de Math\u00e9matiques de Bordeaux.<\/p>\n\n\n\n<div style=\"height:30px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<h5 class=\"wp-block-heading\" id=\"follow-my-research\">Follow my research <\/h5>\n\n\n\n<p><a href=\"https:\/\/scholar.google.fr\/citations?hl=fr&amp;user=1oURadYAAAAJ&amp;view_op=list_works&amp;sortby=pubdate\">Google Scholar <\/a><\/p>\n\n\n\n<p><a href=\"https:\/\/hal.inria.fr\/search\/index\/q\/%2A\/authIdHal_s\/yann-traonmilin\/sort\/producedDate_tdate+desc\/\">HAL<\/a> <\/p>\n\n\n\n<p><a href=\"https:\/\/twitter.com\/YTraonmilin\">Twitter<\/a><\/p>\n\n\n\n<p><a href=\"https:\/\/bsky.app\/profile\/ytraonmilin.bsky.social\">Bluesky<\/a><\/p>\n<\/div>\n<\/div>\n<\/div><\/div>\n\n\n\n<p><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Yann Traonmilin I am a CNRS researcher in the IOP team of the Institut de Math\u00e9matiques de Bordeaux. Follow my research Google Scholar HAL Twitter Bluesky<\/p>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-280","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/yanntraonmilin.perso.math.cnrs.fr\/index.php?rest_route=\/wp\/v2\/pages\/280","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/yanntraonmilin.perso.math.cnrs.fr\/index.php?rest_route=\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/yanntraonmilin.perso.math.cnrs.fr\/index.php?rest_route=\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/yanntraonmilin.perso.math.cnrs.fr\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/yanntraonmilin.perso.math.cnrs.fr\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=280"}],"version-history":[{"count":4,"href":"https:\/\/yanntraonmilin.perso.math.cnrs.fr\/index.php?rest_route=\/wp\/v2\/pages\/280\/revisions"}],"predecessor-version":[{"id":552,"href":"https:\/\/yanntraonmilin.perso.math.cnrs.fr\/index.php?rest_route=\/wp\/v2\/pages\/280\/revisions\/552"}],"wp:attachment":[{"href":"https:\/\/yanntraonmilin.perso.math.cnrs.fr\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=280"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}