{"id":470,"date":"2019-04-21T22:00:28","date_gmt":"2019-04-21T21:00:28","guid":{"rendered":"http:\/\/pageperso.math.univ-toulouse.fr\/gfort\/?page_id=470"},"modified":"2025-02-10T23:13:51","modified_gmt":"2025-02-10T22:13:51","slug":"invited-international-conf","status":"publish","type":"page","link":"https:\/\/perso.math.univ-toulouse.fr\/gfort\/communications\/invited-international-conf\/","title":{"rendered":"Invited, International conf."},"content":{"rendered":"<ol>\n<ol>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Conference &#8220;AI, Science and Society&#8221; of the Artificial Intelligence Action Summit\u00a0<em> Palaiseau, France, February 2025<\/em>.<\/span>\n<ul>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Stochastic Optimization beyond Gradient for Machine Learning. [<a href=\"https:\/\/www.math.univ-toulouse.fr\/%7Egfort\/Slides\/AIconf25_gfort.pdf\">Slides.pdf]<\/a>\u00a0 <\/span><\/li>\n<\/ul>\n<\/li>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">(<strong>plenary speaker<\/strong>) <a href=\"https:\/\/uwaterloo.ca\/monte-carlo-methods-scientific-computing-conference\/\">Monte Carlo and Quasi-Monte Carlo methods in Scientific Computing<\/a>, <em>Waterloo, Canada, August 2024<\/em>.<\/span>\n<ul>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Stochastic Approximation beyond Gradient [<a href=\"https:\/\/www.math.univ-toulouse.fr\/%7Egfort\/Slides\/MCQMC2024.pdf\">slides.pdf<\/a>]<\/span><\/li>\n<\/ul>\n<\/li>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">(<strong>plenary speaker<\/strong>) &#8211;<a href=\"https:\/\/www.unioviedo.es\/fgs2024\/\"> French-German-Spanish conference on Optimization,<\/a><em> Gijon, Spain, June 2024.<\/em><\/span>\n<ul>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Stochastic Approximation beyond Gradient\u00a0[<a href=\"https:\/\/www.math.univ-toulouse.fr\/%7Egfort\/Slides\/FGS2024.pdf\">slides.pdf<\/a>]<br \/>\n<\/span><\/li>\n<\/ul>\n<\/li>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">European Meeting of Statisticians; <em>Warsaw, Poland, July 2023<\/em><\/span>\n<ul>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Stochastic Approximation beyond Gradient [<a href=\"https:\/\/www.math.univ-toulouse.fr\/%7Egfort\/Slides\/IS15_fort.pdf\">slides.pdf<\/a>]<\/span><\/li>\n<\/ul>\n<\/li>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Conference &#8220;Processus markoviens, semi-markoviens et leurs applications&#8221;; <em>Montpellier, France, June 2023<\/em><\/span>\n<ul>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">When Markov chains control Monte Carlo sampling. [<a href=\"https:\/\/www.math.univ-toulouse.fr\/%7Egfort\/Slides\/Markov23.pdf\">slides.pdf<\/a>]<\/span><\/li>\n<\/ul>\n<\/li>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Conference &#8220;Learning and Optimization in Luminy&#8221;, CIRM; <em>Marseille, France, October 2022<\/em><\/span>\n<ul>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Stochastic Variable Metric Forward-Backward with variance reduction for non-convex optimization [<a href=\"https:\/\/www.math.univ-toulouse.fr\/%7Egfort\/Slides\/Luminy22.pdf\">slides.pdf<\/a>]<\/span><\/li>\n<\/ul>\n<\/li>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Workshop &#8220;Current developments in MCMC methods&#8221;, Banach Center; <em>Warsaw, Poland; December 2021.<\/em><\/span>\n<ul>\n<li style=\"text-align: justify\">Federated E<span style=\"font-size: 12pt\">xpectation Maximization with heterogeneity mitigation and variance reduction.\u00a0 [<a href=\"https:\/\/www.math.univ-toulouse.fr\/%7Egfort\/Slides\/SlidesWarsaw21.pdf\">slides.pdf<\/a>]<\/span><\/li>\n<\/ul>\n<\/li>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Conference &#8220;Future Synergies for Stochastic and Learning algorithms&#8221;, CIRM; <em>Marseille, France; September 2021 <\/em><\/span><\/li>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Conference in Numerical Probability, in honour of Gilles Pag\u00e8s; <em>Paris, France; September 2020 (postponed in May 2021)<\/em><\/span>\n<ul>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">A Variance Reduced Expectation Maximization algorithm for finite-sum optimization [<a href=\"https:\/\/www.math.univ-toulouse.fr\/%7Egfort\/Slides\/GillesPages.pdf\">slides.pdf<\/a>] and <a href=\"https:\/\/www.youtube.com\/watch?v=kN6r8zv_6RA\">video<\/a><br \/>\n<\/span><\/li>\n<\/ul>\n<\/li>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\"><del>Conference &#8220;Structural Inference in High Dimensional Models&#8221;; <\/del><em><del>Bordeaux, France; August 2020<\/del> (Canceled, Covid19)<br \/>\n<\/em><\/span><\/li>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\"><del>Summer School 2020, Indo-French Centre for Applied Mathematics; <\/del><em><del>Bangalore, India; July 2020<\/del> (Canceled, Covid19)<br \/>\n<\/em><\/span><\/li>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Conference &#8220;Optimization for Machine Learning&#8221;, CIRM; <em>Marseille, France<\/em>; <em>March 2020<\/em><\/span>\n<ul>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Fast Incremental Expectation Maximization algorithm: how many iterations for an \\epsilon-stationary point ? [<a href=\"https:\/\/www.math.univ-toulouse.fr\/%7Egfort\/Slides\/CIRM20.pdf\">slides.pdf<\/a>]<br \/>\n<\/span><\/li>\n<\/ul>\n<\/li>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">(plenary speaker) BayesComp 2020; <em>Gainesville, USA; January 2020.<\/em><\/span>\n<ul>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\"><em>invitation declined for professional duties (new schedule of a HCERES evaluation).\u00a0<\/em> <\/span><\/li>\n<\/ul>\n<\/li>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\"><strong>(3 lectures and a talk) <\/strong>Advances in Applied Probability (ICTS Program); <em>Bengaluru, India; August 2019.<\/em><\/span>\n<ul>\n<li><span style=\"font-size: 12pt\">When Monte Carlo and Optimization met in a Markovian dance\u00a0\u00a0 [<a href=\"https:\/\/www.math.univ-toulouse.fr\/%7Egfort\/Slides\/Inde19-Talk-abstract.pdf\">abstract.pdf<\/a>]<\/span>\n<ul>\n<li>Lecture 1 : Computational Statistical Learning [<a href=\"https:\/\/www.math.univ-toulouse.fr\/%7Egfort\/Slides\/Inde19-Talk-part1.pdf\">slides.pdf<\/a>] [<a href=\"http:\/\/live.icts.res.in\/videos\/video\/5382\/\">channel<\/a>]<\/li>\n<li>Lecture 2 : Controlled Markov chains [<a href=\"http:\/\/live.icts.res.in\/videos\/video\/5385\/\">slides.pdf] [channel]<\/a><\/li>\n<li>Lecture 3 : Stochastic Approximation with Markovian Dynamics [<a href=\"https:\/\/www.math.univ-toulouse.fr\/%7Egfort\/Slides\/Inde19-Talk-Part3.pdf\">slides.pdf<\/a>] [<a href=\"http:\/\/live.icts.res.in\/videos\/video\/5387\/\">channel<\/a>]<\/li>\n<li>Talk:\u00a0 Stochastic Proximal-Gradient based algorithms: is Nesterov acceleration efficient ? [<a href=\"https:\/\/www.math.univ-toulouse.fr\/%7Egfort\/Slides\/Inde19-Talk-part4.pdf\">slides.pdf<\/a>] [<a href=\"http:\/\/live.icts.res.in\/videos\/video\/5391\/\">channel<\/a>]<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\"><strong>(plenary speaker)<\/strong> Twelth International Conference on Monte Carlo methods and Applications (MCM2019); <em>Sydney, Australie; July 2019.<\/em><\/span>\n<ul>\n<li><span style=\"font-size: 12pt\">Monte Carlo methods and Optimization: Intertwinings [<a href=\"https:\/\/www.math.univ-toulouse.fr\/%7Egfort\/Slides\/MCM19.pdf\">slides.pdf<\/a>] [<a href=\"https:\/\/www.math.univ-toulouse.fr\/%7Egfort\/Slides\/MCM19-photo.jpeg\">group photo<\/a>]<br \/>\n<\/span><\/li>\n<\/ul>\n<\/li>\n<li><span style=\"font-size: 12pt\">Workshop &#8220;The mathematics of imaging&#8221;; <em>Paris, France; February 2019.<\/em><\/span>\n<ul>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Stochastic Approximation-based algorithms, when the Monte Carlo bias does not vanish [<a href=\"https:\/\/www.math.univ-toulouse.fr\/%7Egfort\/Slides\/IHP19.pdf\">slides.pdf<\/a>] [<a href=\"https:\/\/www.youtube.com\/watch?v=EqRNDmPwyyQ\">video]<\/a><br \/>\n<\/span><\/li>\n<\/ul>\n<\/li>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Workshop &#8220;Computational Statistics and Molecular Simulations: a practical cross-fertilization&#8221;, BIRS; <em>Oaxaca, Mexico; November 2018.<\/em><\/span>\n<ul>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Convergence and Efficiency of Adaptive Importance Sampling techniques with partial biasing [<a href=\"http:\/\/math.univ-toulouse.fr\/%7Egfort\/Slides\/Slides_Oaxa18.pdf\">slides.pdf<\/a>] [<a href=\"http:\/\/videos.birs.ca\/2018\/18w5023\/201811151634-Fort.mp4\">video<\/a>]<\/span><\/li>\n<\/ul>\n<\/li>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Workshop &#8220;Operator Splitting methods in Data Analysis&#8221;; <em>Raleigh, USA; March 2018.<\/em><\/span>\n<ul>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Perturbed (accelerated) Proximal-Gradient Algorithms [<a href=\"http:\/\/math.univ-toulouse.fr\/%7Egfort\/Slides\/Slides_Raleigh18.pdf\">slides.pdf<\/a>]<\/span><\/li>\n<\/ul>\n<\/li>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Foundations of Computational Mathematics (FOCM), Workshop &#8220;Stochastic Computation&#8221;; <em>Barcelona, Spain; July 2017.<\/em><\/span>\n<ul>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Beyond Well-tempered Metadynamics algorithms for sampling multimodal target densities [<a href=\"http:\/\/math.univ-toulouse.fr\/%7Egfort\/Slides\/Slides_Barcelone17.pdf\">slides.pdf<\/a>]<\/span><\/li>\n<\/ul>\n<\/li>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">11th International Conference on Monte Carlo methods and Applications; <em>Montreal, Canada; July 2017.<\/em><\/span>\n<ul>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">MCMC design-based non-parametric regression for rare-event. Application to nested rosk computations [<a href=\"http:\/\/math.univ-toulouse.fr\/%7Egfort\/Slides\/Slides_Montreal17.pdf\">slides.pdf<\/a>]<\/span><\/li>\n<\/ul>\n<\/li>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">International Conference on Monte Carlo techniques (closing conferene of a thematic cycle); <em>Paris, France; July 2016.<\/em><\/span>\n<ul>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Nested risk computations through non parametric regression with Markovian design [<a href=\"http:\/\/math.univ-toulouse.fr\/%7Egfort\/Slides\/Slides_Paris16.pdf\">slides.pdf<\/a>]<\/span><\/li>\n<\/ul>\n<\/li>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Workshop &#8220;Stochastic Algorithms for Big Data&#8221;; Paris, France; July 2016.\u00a0 <\/span>\n<ul>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Stochastic Perturbations of Proximal-Gradient methods for non-smooth convex optimization: the price of Markovian perturbations\u00a0 [<a href=\"https:\/\/www.math.univ-toulouse.fr\/%7Egfort\/Slides\/bigdata16.pdf\">slides.pdf<\/a>]<\/span><\/li>\n<\/ul>\n<\/li>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Workshop &#8220;High Dimensional Statistical Models &amp; Big Data&#8221;, Alan Turing Institute; <em>London, United Kingdom; February 2016.<\/em><\/span>\n<ul>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Convergence of Perturbed Gradient-based methods for non-smooth convex optimization [<a href=\"http:\/\/math.univ-toulouse.fr\/%7Egfort\/Slides\/ATI_gersende_fort.pdf\">slides.pdf<\/a>]<\/span><\/li>\n<\/ul>\n<\/li>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Workshop &#8220;Free energy calculations: a mathematical perspective&#8221;, BIRS; <em>Oaxaca, Mexico; July 2015.<\/em><\/span>\n<ul>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Mathematical aspects of adaptive samplers: application to free energy calculation. [<a href=\"http:\/\/math.univ-toulouse.fr\/%7Egfort\/Slides\/Oaxaca15.pdf\">slides.pdf<\/a>][<a href=\"http:\/\/www.birs.ca\/events\/2015\/5-day-workshops\/15w5128\/videos\/watch\/201507230906-Fort.html\">video<\/a>][<a href=\"http:\/\/www.birs.ca\/cmo-workshops\/2015\/15w5128\/groupphoto.jpg\">photo<\/a>]<\/span><\/li>\n<\/ul>\n<\/li>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">International Conference &#8220;7th Journ\u00e9es de Statistique du Sud&#8221;; <em>Barcelona, Spain; June 2014.<\/em><\/span>\n<ul>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Sampling multimodal densities on large dimensional spaces [<a href=\"http:\/\/math.univ-toulouse.fr\/%7Egfort\/Slides\/Barcelone14.pdf\">slides.pdf<\/a>][<a href=\"http:\/\/math.univ-toulouse.fr\/%7Egfort\/Slides\/PhotoBarcelone14.JPG\">photo<\/a>]<\/span><\/li>\n<\/ul>\n<\/li>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Workshop &#8220;Computational methods for statistical mechanics&#8221;; <em>Edinburgh, United Kingdom; July 2014.<\/em><\/span>\n<ul>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Convergence and Efficiency of the Wang Landau algorithm [<a href=\"http:\/\/math.univ-toulouse.fr\/%7Egfort\/Slides\/Edimbourg14.pdf\">slides.pdf<\/a>]<\/span><\/li>\n<\/ul>\n<\/li>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Workshop &#8220;From spectral gap to particle filters&#8221;; <em>Reading, United Kingdom; September 2013.<\/em><\/span>\n<ul>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Adaptive and Interacting Markov chain Monte Carlo [<a href=\"https:\/\/www.math.univ-toulouse.fr\/%7Egfort\/Slides\/Reading13.pdf\">slides.pdf<\/a>]<\/span><\/li>\n<\/ul>\n<\/li>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Workshop &#8220;New directions in Monte Carlo methods&#8221;; <em>Gainesville, USA; January 2013.<\/em><\/span>\n<ul>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Convergence and Efficiency of the Wang Landau algorithm [<a href=\"http:\/\/math.univ-toulouse.fr\/%7Egfort\/Slides\/Gainesville13.pdf\">slides.pdf<\/a>][<a href=\"http:\/\/math.univ-toulouse.fr\/%7Egfort\/Slides\/PhotoGainesville13.JPG\">photo<\/a>]<\/span><\/li>\n<\/ul>\n<\/li>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Workshop &#8220;Big Bang, Big Data, Big Computers&#8221;; <em>Paris, France; September 2012.<\/em><\/span>\n<ul>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Adaptive abd Interacting Monte Carlo methods for bayesian analysis [<a href=\"http:\/\/math.univ-toulouse.fr\/%7Egfort\/Slides\/APC2012.pdf\">slides.pdf<\/a>]<\/span><\/li>\n<\/ul>\n<\/li>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">ISBA conference 2012; <em>Kyoto, Japan; June 2012.<\/em><\/span>\n<ul>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Adaptive Equi-Energy samplers [<a href=\"http:\/\/math.univ-toulouse.fr\/%7Egfort\/Slides\/gfort_ISBA12.pdf\">slides.pdf<\/a>]<\/span><\/li>\n<\/ul>\n<\/li>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Workshop &#8220;Advances in Markov chain Monte Carlo&#8221;; <em>Edinburgh, United Kingdom; April 2012.<\/em><\/span>\n<ul>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Stochastic Approximation-based adaptation for Interacting MCMC [<a href=\"http:\/\/math.univ-toulouse.fr\/%7Egfort\/Slides\/gfort_ICMS12.pdf\">slides.pdf<\/a>]<\/span><\/li>\n<\/ul>\n<\/li>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Workshop\u00a0 &#8220;Challenges and Advances in High Dimensional and High Complexity Monte Carlo Computation and Theory&#8221;; <em>Calgary, Canada; March 2012.<\/em><\/span>\n<ul>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Parallel Tempering and interacting algorithms &#8211; Part II: adaptive equi-enery samplers [<a href=\"http:\/\/math.univ-toulouse.fr\/%7Egfort\/Slides\/gfort_ICMS12.pdf\">slides.pdf<\/a>][<a href=\"http:\/\/math.univ-toulouse.fr\/%7Egfort\/Slides\/PhotoBanff12.jpg\">photo<\/a>]<\/span><\/li>\n<\/ul>\n<\/li>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Conference MCQMC 2010; <em>Warsaw, Poland; August 2010.<\/em><\/span>\n<ul>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Convergence of Adaptive and Interacting MCMC algorithms [<a href=\"http:\/\/math.univ-toulouse.fr\/%7Egfort\/Slides\/MCQMC10.pdf\">slides.pdf<\/a>]<\/span><\/li>\n<\/ul>\n<\/li>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Conference &#8220;Optimization in MCMC&#8221;;<em> Warwick, United Kingdom; June 2009.<\/em><\/span>\n<ul>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Adaptive MCMC: theory and methods [slides.pdf]<\/span><\/li>\n<\/ul>\n<\/li>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Congr\u00e8s SSC-SFDS; <em>Ottawa, Canada; May 2008.<\/em><\/span>\n<ul>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Stability of Markov chains based on fluid limit techniques. Applications to MCMC [<a href=\"http:\/\/math.univ-toulouse.fr\/%7Egfort\/Slides\/Ottawa08.pdf\">slides.pdf<\/a>]<\/span><\/li>\n<\/ul>\n<\/li>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">ADAP&#8217;ski; <em>Bormio, Italy; January 2008.<\/em><\/span>\n<ul>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Fluid limit-based tuning of some hybrid MCMC samplers [<a href=\"http:\/\/math.univ-toulouse.fr\/%7Egfort\/Slides\/Bormio08.pdf\">slides.pdf<\/a>]<\/span><\/li>\n<\/ul>\n<\/li>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Workshop &#8220;New developments in MCMC: diffusions, images and other challenges&#8221;; <em>Warwick, United Kingdom; August 2006.<\/em><\/span>\n<ul>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Criteria for subgeometric ergodicity of strong Markov processes [<a href=\"http:\/\/math.univ-toulouse.fr\/%7Egfort\/Slides\/Warwick06Beamer.pdf\">slides.pdf<\/a>]<\/span><\/li>\n<\/ul>\n<\/li>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Workshop &#8220;MCMC methodology&#8221;; <em>Lancaster, United Kingdom; December 2001.<\/em><\/span>\n<ul>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Talk 1 &#8220;Some recent results on Hybrid samplers&#8221; [<a href=\"http:\/\/math.univ-toulouse.fr\/%7Egfort\/Slides\/lancaster_hybride.ps\">slides.ps<\/a>]<\/span><\/li>\n<\/ul>\n<\/li>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Workshop &#8220;MCMC methodology&#8221;;<em> Lancaster, United Kingdom; December 2001.<\/em><\/span>\n<ul>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">Talk 2 &#8220;Convergence of the MCEM algorithm&#8221; [<a href=\"http:\/\/math.univ-toulouse.fr\/%7Egfort\/Slides\/lancaster_mcem.ps\">slides.ps<\/a>]<\/span><\/li>\n<\/ul>\n<\/li>\n<li style=\"text-align: justify\"><span style=\"font-size: 12pt\">European conference on Spatial and Computational Statistics; <em>Ambleside, United Kingdom; September 2000.<\/em><\/span><\/li>\n<\/ol>\n<\/ol>\n<p>&nbsp;<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Conference &#8220;AI, Science and Society&#8221; of the Artificial Intelligence Action Summit\u00a0 Palaiseau, France, February 2025. Stochastic Optimization beyond Gradient for Machine Learning. [Slides.pdf]\u00a0 (plenary speaker) Monte Carlo and Quasi-Monte Carlo methods in Scientific Computing, Waterloo, Canada, August 2024. Stochastic Approximation beyond Gradient [slides.pdf] (plenary speaker) &#8211; French-German-Spanish conference on Optimization, Gijon, Spain, June 2024. Stochastic [&hellip;]<\/p>\n","protected":false},"author":194,"featured_media":0,"parent":76,"menu_order":1,"comment_status":"closed","ping_status":"open","template":"full-width-page.php","meta":{"footnotes":""},"class_list":["post-470","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/perso.math.univ-toulouse.fr\/gfort\/wp-json\/wp\/v2\/pages\/470","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=470"}],"version-history":[{"count":113,"href":"https:\/\/perso.math.univ-toulouse.fr\/gfort\/wp-json\/wp\/v2\/pages\/470\/revisions"}],"predecessor-version":[{"id":5666,"href":"https:\/\/perso.math.univ-toulouse.fr\/gfort\/wp-json\/wp\/v2\/pages\/470\/revisions\/5666"}],"up":[{"embeddable":true,"href":"https:\/\/perso.math.univ-toulouse.fr\/gfort\/wp-json\/wp\/v2\/pages\/76"}],"wp:attachment":[{"href":"https:\/\/perso.math.univ-toulouse.fr\/gfort\/wp-json\/wp\/v2\/media?parent=470"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}