{"id":6178,"date":"2025-06-06T17:01:59","date_gmt":"2025-06-06T15:01:59","guid":{"rendered":"https:\/\/datascience.unifi.it\/?post_type=tribe_events&#038;p=6178"},"modified":"2026-01-24T12:14:09","modified_gmt":"2026-01-24T11:14:09","slug":"webinar-mohammad-jafari-jozani","status":"publish","type":"tribe_events","link":"https:\/\/datascience.unifi.it\/index.php\/event\/webinar-mohammad-jafari-jozani\/","title":{"rendered":"Webinar: Mohammad Jafari Jozani"},"content":{"rendered":"<p>On-site and online<strong> seminar: Tuesday, July 1st 2025 <\/strong>from <strong>2.00 &#8211; 3.00 PM<\/strong><\/p>\n<h3>Title:\u00a0<span style=\"color: #992800;\"><strong>Rethinking Support in SVMs: An Elite-Driven Approach to Classification<\/strong><\/span><\/h3>\n<h3>Speaker: <span style=\"color: #992800;\">Mohammad Jafari Jozani (University of Manitoba)<\/span><\/h3>\n<h3>Location: Aula 205 (ex 32) &#8211; Viale Morgagni 59<\/h3>\n<p>Please register here to participate online : <a href=\"https:\/\/events.teams.microsoft.com\/event\/03129c92-0f77-45fa-8450-a7690e52bc02@af7fbb09-23f3-4aff-8e08-0e4bec0d9ee7\">link<\/a><\/p>\n<p><strong>ABSTRACT<\/strong><\/p>\n<div>\n<div>\n<p>Support Vector Machines (SVMs) are a cornerstone of classification methodology, where decision boundaries are shaped by support vectors determined via a chosen loss function. However, different loss functions yield different sets of support vectors, resulting in variable classification outcomes. This conventional dependence on a single loss function often obscures broader structural insights\u2014particularly the presence of observations that consistently act as support vectors across multiple SVM configurations. These persistently influential points point to a new paradigm in classifier design.<\/p>\n<p>We propose\u00a0<strong>Elite-Driven Support Vector Machines (EDSVM)<\/strong>, a novel framework that enhances classification performance by identifying and amplifying the role of these elite observations. These elites are data points that recur as support vectors across a range of loss functions and decision boundaries. To harness their importance, we design new classification-calibrated loss functions that embed elite-weighted influence directly into the training process.<\/p>\n<p>Through rigorous theoretical development and extensive empirical evaluation\u2014spanning both synthetic and real-world datasets\u2014we show that EDSVM outperforms classical SVMs in linear and nonlinear settings. This work advances the foundations of SVM methodology and offers practical tools for high-stakes, data-sensitive applications.<\/p>\n<\/div>\n<\/div>\n","protected":false},"excerpt":{"rendered":"<p>On-site and online seminar: Tuesday, July 1st 2025 from 2.00 &#8211; 3.00 PM Title:\u00a0Rethinking Support in SVMs: An Elite-Driven Approach to Classification Speaker: Mohammad Jafari Jozani (University of Manitoba) Location: &#8230;<\/p>\n","protected":false},"author":26,"featured_media":0,"template":"","meta":{"_monsterinsights_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0,"_tribe_events_status":"","_tribe_events_status_reason":"","footnotes":""},"tags":[],"tribe_events_cat":[35],"class_list":["post-6178","tribe_events","type-tribe_events","status-publish","hentry","tribe_events_cat-seminar","cat_seminar"],"_links":{"self":[{"href":"https:\/\/datascience.unifi.it\/index.php\/wp-json\/wp\/v2\/tribe_events\/6178","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/datascience.unifi.it\/index.php\/wp-json\/wp\/v2\/tribe_events"}],"about":[{"href":"https:\/\/datascience.unifi.it\/index.php\/wp-json\/wp\/v2\/types\/tribe_events"}],"author":[{"embeddable":true,"href":"https:\/\/datascience.unifi.it\/index.php\/wp-json\/wp\/v2\/users\/26"}],"version-history":[{"count":3,"href":"https:\/\/datascience.unifi.it\/index.php\/wp-json\/wp\/v2\/tribe_events\/6178\/revisions"}],"predecessor-version":[{"id":6182,"href":"https:\/\/datascience.unifi.it\/index.php\/wp-json\/wp\/v2\/tribe_events\/6178\/revisions\/6182"}],"wp:attachment":[{"href":"https:\/\/datascience.unifi.it\/index.php\/wp-json\/wp\/v2\/media?parent=6178"}],"wp:term":[{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/datascience.unifi.it\/index.php\/wp-json\/wp\/v2\/tags?post=6178"},{"taxonomy":"tribe_events_cat","embeddable":true,"href":"https:\/\/datascience.unifi.it\/index.php\/wp-json\/wp\/v2\/tribe_events_cat?post=6178"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}