{"id":49,"date":"2024-12-16T14:18:22","date_gmt":"2024-12-16T13:18:22","guid":{"rendered":"https:\/\/hub.imt-atlantique.fr\/gmlas\/?page_id=49"},"modified":"2026-01-12T09:28:24","modified_gmt":"2026-01-12T08:28:24","slug":"project-description","status":"publish","type":"page","link":"https:\/\/hub.imt-atlantique.fr\/gmlas\/?page_id=49","title":{"rendered":"Project description"},"content":{"rendered":"\n<p class=\"has-text-align-left has-medium-font-size\">Current research at the intersection of <strong>Combinatorial Optimization  (CO)<\/strong> and <strong>Machine Learning (ML)<\/strong> is emerging as a game-changing force in Artificial Intelligence. This fusion of two traditionally distinct solving paradigms has recently gained strong momentum in the CO community and is becoming a ubiquitous technology across a wide range of applications. One area that can particularly benefit from ML is <strong>constraint reasoning and optimization<\/strong>.<\/p>\n\n\n\n<p class=\"has-medium-font-size\"><strong>Constraint Programming (CP)<\/strong> is widely regarded as one of the foremost paradigms for solving combinatorial problems in AI. CP provides a generic and expressive framework for modeling and solving problems arising in diverse application domains. However, the hybridization of <strong>Data Mining, Machine Learning, and Deep Learning<\/strong> with state-of-the-art <strong>discrete reasoning and optimization techniques<\/strong> remains one of the major challenges in AI.<\/p>\n\n\n\n<p class=\"has-medium-font-size\">This proposal addresses the challenge of <strong>data-driven decision making<\/strong> through a unified framework combining <strong>machine learning<\/strong>, <strong>discrete reasoning and optimization<\/strong>, and an associated solver based on <strong>Graphical Models (GMs)<\/strong>, namely <strong><a href=\"https:\/\/github.com\/toulbar2\/toulbar2\">toulbar2<\/a><\/strong>\u2014winner of the <a href=\"https:\/\/uaicompetition.github.io\/uci-2022\/results\/benchmarks\/\">UAI 2022<\/a> solver competition on two discrete optimization and counting tasks. Discrete graphical models, particularly <strong>additive GMs<\/strong> such as <strong>Cost Function Networks (CFNs)<\/strong> and <strong>Markov Random Fields (MRFs)<\/strong>, are especially attractive as they naturally and seamlessly integrate logical and probabilistic information. The <strong>toulbar2<\/strong> solver is a state-of-the-art tool for reasoning over such models, supporting both exact algorithms and advanced meta-heuristics.<\/p>\n\n\n\n<p class=\"has-text-align-left has-medium-font-size\">The <strong>GMLaS<\/strong> project represents a significant step toward the ambitious goal of integrating <strong>ML\/DM tools within the Cost Function Network paradigm<\/strong>, leading to a <strong>hybrid, data-driven solving framework<\/strong> that natively addresses optimization problems and aims to scale to larger and more complex real-world applications. One key application targeted by the project is <strong>computational protein design (CPD)<\/strong>, a domain in which one of the project partners has deep and well-established expertise.<\/p>\n\n\n\n<p class=\"has-medium-font-size\"><\/p>\n\n\n\n<p><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Current research at the intersection of Combinatorial Optimization (CO) and Machine Learning (ML) is emerging as a game-changing force in Artificial Intelligence. This fusion of two traditionally distinct solving paradigms has recently gained strong momentum in the CO community and is becoming a ubiquitous technology across a wide range of applications. One area that can &hellip; <a href=\"https:\/\/hub.imt-atlantique.fr\/gmlas\/?page_id=49\" class=\"more-link\">Continuer la lecture de <span class=\"screen-reader-text\">Project description<\/span><\/a><\/p>\n","protected":false},"author":2,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-49","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/hub.imt-atlantique.fr\/gmlas\/index.php?rest_route=\/wp\/v2\/pages\/49","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/hub.imt-atlantique.fr\/gmlas\/index.php?rest_route=\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/hub.imt-atlantique.fr\/gmlas\/index.php?rest_route=\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/hub.imt-atlantique.fr\/gmlas\/index.php?rest_route=\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/hub.imt-atlantique.fr\/gmlas\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=49"}],"version-history":[{"count":6,"href":"https:\/\/hub.imt-atlantique.fr\/gmlas\/index.php?rest_route=\/wp\/v2\/pages\/49\/revisions"}],"predecessor-version":[{"id":260,"href":"https:\/\/hub.imt-atlantique.fr\/gmlas\/index.php?rest_route=\/wp\/v2\/pages\/49\/revisions\/260"}],"wp:attachment":[{"href":"https:\/\/hub.imt-atlantique.fr\/gmlas\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=49"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}