pr\u00e9sentent<\/p>\n\n\n\n
Autoris\u00e9 \u00e0 pr\u00e9senter ses travaux en vue de l\u2019obtention du Doctorat de l’Institut Polytechnique de Paris, pr\u00e9par\u00e9 \u00e0 T\u00e9l\u00e9com SudParis en :<\/p>\n\n\n\n
le JEUDI 28 SEPTEMBRE 2023 \u00e0 15h00<\/strong> \u00e0 la Salle 16-26-209 (Salle Paul L\u00e9vy)<\/strong> Membres du jury :<\/strong><\/p>\n\n\n\n M. Sylvain LE CORFF<\/strong>, Professeur, Sorbonne Universit\u00e9, FRANCE – Directeur de these R\u00e9sum\u00e9 :<\/strong><\/p>\n\n\n\n Cette th\u00e8se contribue au vaste domaine des m\u00e9thodes de Monte Carlo avec de nouveaux algorithmes visant \u00e0 traiter l’inf\u00e9rence en grande dimension et la quantification de l’incertitude. Dans une premi\u00e8re partie, nous d\u00e9veloppons deux nouvelles m\u00e9thodes pour l’\u00e9chantillonnage d’importance. Le premier algorithme est une nouvelle loi de proposition, bas\u00e9e sur sur des \u00e9tapes d\u2019optimisation et de co\u00fbt de calcul faible, pour le calcul des constantes de normalisation. L’algorithme r\u00e9sultant est ensuite \u00e9tendu en un nouvel algorithme MCMC. Le deuxi\u00e8me algorithme est un nouveau sch\u00e9ma pour l’apprentissage de propositions d’importance adapt\u00e9es aux cibles complexes et multimodales. Dans une deuxi\u00e8me partie, nous nous concentrons sur les m\u00e9thodes de Monte Carlo s\u00e9quentielles. Nous d\u00e9veloppons de nouveaux estimateurs de la variance asymptotique du filtre \u00e0 particules et fournissons le premier estimateur de la variance asymptotique d’un lisseur \u00e0 particules. Ensuite, nous proposons une proc\u00e9dure d’apprentissage des param\u00e8tres dans les mod\u00e8les de Markov cach\u00e9s en utilisant un lisseur \u00e0 particules dont le biais est r\u00e9duit par rapport aux m\u00e9thodes existantes. Enfin, nous concevons un algorithme de Monte Carlo s\u00e9quentiel pour r\u00e9soudre des probl\u00e8mes inverses lin\u00e9aires bay\u00e9siens avec des lois a priori obtenues par mod\u00e8les g\u00e9n\u00e9ratifs.<\/p>\n\n\n\n This thesis contributes to the vast domain of Monte Carlo methods with novel algorithms that aim at adressing high dimensional inference and uncertainty quantification. In a first part, we develop two novel methods for Importance Sampling. The first algorithm is a lightweight optimization based proposal for computing normalizing constants and which extends into a novel MCMC algorithm. The second one is a new scheme for learning sharp importance proposals. In a second part, we focus on Sequential Monte Carlo methods. We develop new estimators for the asymptotic variance of the particle filter and provide the first estimator of the asymptotic variance of a particle smoother. Next, we derive a procedure for parameter learning within hidden Markov models using a particle smoother with provably reduced bias. Finally, we devise a Sequential Monte Carlo algorithm for solving Bayesian linear inverse problems with generative model priors.<\/p>\n","protected":false},"excerpt":{"rendered":" L’Ecole doctorale : Math\u00e9matiques Hadamard et le Laboratoire de recherche SAMOVAR – Services r\u00e9partis, Architectures, Mod\u00e9lisation, Validation, Administration des R\u00e9seaux pr\u00e9sentent l\u2019AVIS DE SOUTENANCE de Monsieur Yazid JANATI EL IDRISSI Autoris\u00e9 \u00e0 pr\u00e9senter ses travaux en vue de l\u2019obtention du Doctorat de l’Institut Polytechnique de Paris, pr\u00e9par\u00e9 \u00e0 T\u00e9l\u00e9com SudParis en : \u00ab M\u00e9thodes Monte […]<\/p>\n","protected":false},"author":4,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"ocean_post_layout":"","ocean_both_sidebars_style":"","ocean_both_sidebars_content_width":0,"ocean_both_sidebars_sidebars_width":0,"ocean_sidebar":"0","ocean_second_sidebar":"0","ocean_disable_margins":"enable","ocean_add_body_class":"","ocean_shortcode_before_top_bar":"","ocean_shortcode_after_top_bar":"","ocean_shortcode_before_header":"","ocean_shortcode_after_header":"","ocean_has_shortcode":"","ocean_shortcode_after_title":"","ocean_shortcode_before_footer_widgets":"","ocean_shortcode_after_footer_widgets":"","ocean_shortcode_before_footer_bottom":"","ocean_shortcode_after_footer_bottom":"","ocean_display_top_bar":"default","ocean_display_header":"default","ocean_header_style":"","ocean_center_header_left_menu":"0","ocean_custom_header_template":"0","ocean_custom_logo":0,"ocean_custom_retina_logo":0,"ocean_custom_logo_max_width":0,"ocean_custom_logo_tablet_max_width":0,"ocean_custom_logo_mobile_max_width":0,"ocean_custom_logo_max_height":0,"ocean_custom_logo_tablet_max_height":0,"ocean_custom_logo_mobile_max_height":0,"ocean_header_custom_menu":"0","ocean_menu_typo_font_family":"0","ocean_menu_typo_font_subset":"","ocean_menu_typo_font_size":0,"ocean_menu_typo_font_size_tablet":0,"ocean_menu_typo_font_size_mobile":0,"ocean_menu_typo_font_size_unit":"px","ocean_menu_typo_font_weight":"","ocean_menu_typo_font_weight_tablet":"","ocean_menu_typo_font_weight_mobile":"","ocean_menu_typo_transform":"","ocean_menu_typo_transform_tablet":"","ocean_menu_typo_transform_mobile":"","ocean_menu_typo_line_height":0,"ocean_menu_typo_line_height_tablet":0,"ocean_menu_typo_line_height_mobile":0,"ocean_menu_typo_line_height_unit":"","ocean_menu_typo_spacing":0,"ocean_menu_typo_spacing_tablet":0,"ocean_menu_typo_spacing_mobile":0,"ocean_menu_typo_spacing_unit":"","ocean_menu_link_color":"","ocean_menu_link_color_hover":"","ocean_menu_link_color_active":"","ocean_menu_link_background":"","ocean_menu_link_hover_background":"","ocean_menu_link_active_background":"","ocean_menu_social_links_bg":"","ocean_menu_social_hover_links_bg":"","ocean_menu_social_links_color":"","ocean_menu_social_hover_links_color":"","ocean_disable_title":"default","ocean_disable_heading":"default","ocean_post_title":"","ocean_post_subheading":"","ocean_post_title_style":"","ocean_post_title_background_color":"","ocean_post_title_background":0,"ocean_post_title_bg_image_position":"","ocean_post_title_bg_image_attachment":"","ocean_post_title_bg_image_repeat":"","ocean_post_title_bg_image_size":"","ocean_post_title_height":0,"ocean_post_title_bg_overlay":0.5,"ocean_post_title_bg_overlay_color":"","ocean_disable_breadcrumbs":"default","ocean_breadcrumbs_color":"","ocean_breadcrumbs_separator_color":"","ocean_breadcrumbs_links_color":"","ocean_breadcrumbs_links_hover_color":"","ocean_display_footer_widgets":"default","ocean_display_footer_bottom":"default","ocean_custom_footer_template":"0","ocean_post_oembed":"","ocean_post_self_hosted_media":"","ocean_post_video_embed":"","ocean_link_format":"","ocean_link_format_target":"self","ocean_quote_format":"","ocean_quote_format_link":"post","ocean_gallery_link_images":"off","ocean_gallery_id":[],"footnotes":""},"categories":[286,615],"tags":[],"class_list":["post-6331","post","type-post","status-publish","format-standard","hentry","category-fractualites-ennews-fr","category-seminaire-sop","entry"],"_links":{"self":[{"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/posts\/6331","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/users\/4"}],"replies":[{"embeddable":true,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/comments?post=6331"}],"version-history":[{"count":2,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/posts\/6331\/revisions"}],"predecessor-version":[{"id":6333,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/posts\/6331\/revisions\/6333"}],"wp:attachment":[{"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/media?parent=6331"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/categories?post=6331"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/tags?post=6331"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
Campus Pierre et Marie Curie, 4 place Jussieu 75005 PARIS<\/strong><\/p>\n\n\n\n
M. Jean-Michel MARIN<\/strong>, Professeur, Universit\u00e9 de Montpellier, FRANCE – Rapporteur
M. Anthony LEE<\/strong>, Professeur, University Of Bristol, ROYAUME-UNI – Rapporteur
Mme Marylou GABRIE<\/strong>, Ma\u00eetre de conf\u00e9rences, Ecole polytechnique , FRANCE – Examinateur
M. Jean-Marc BARDET<\/strong>, Professeur, Universiyt\u00e9 Panth\u00e9on Sorbonne (Paris 1), FRANCE – Examinateur
M. Yohan PETETIN<\/strong>, Ma\u00eetre de conf\u00e9rences, T\u00e9l\u00e9com SudParis, FRANCE – CoDirecteur de these<\/p>\n\n\n\n\u00ab M\u00e9thodes Monte Carlo pour l’apprentissage automatique: contributions pratiques et th\u00e9oriques pour l’\u00e9chantillonnage pr\u00e9ferentiel et les m\u00e9thodes s\u00e9quentielles \u00bb<\/h2>\n\n\n\n
pr\u00e9sent\u00e9 par Monsieur Yazid JANATI EL IDRISSI<\/h2>\n\n\n\n
Abstract :<\/strong><\/p>\n\n\n\n