BEGIN:VCALENDAR VERSION:2.0 PRODID:-//wp-events-plugin.com//7.2.3.1//EN TZID:Europe/Paris X-WR-TIMEZONE:Europe/Paris BEGIN:VEVENT UID:6219@i2m.univ-amu.fr DTSTART;TZID=Europe/Paris:20211213T000000 DTEND;TZID=Europe/Paris:20211217T000000 DTSTAMP:20241211T155307Z URL:https://www.i2m.univ-amu.fr/evenements/meeting-in-mathematical-statist ics-2021/ SUMMARY:Conference (CIRM\, Luminy\, Marseille): Meeting in Mathematical Sta tistics 2021 DESCRIPTION:Conference: \n\n\n\n\n\n\n Time Schedule - Abstracts\n\n\n\n Pa rticipants \n\n\n\n\n\n Videos (after the event) \n\n\n\n\n\n Archives MMS 2020 \n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nMULTIYEAR PROGRAM\nCONFERENCE\n​ \nMeeting in Mathematical Statistics   /   Rencontres de Statistique M athématique\nMachine learning and nonparametric statistics\n13 - 17 Decem ber 2021\n\n\n\n\n  \n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nScientific Comm ittee &\; Organizing Committee\nComité scientifique &\; Comité d 'organisation\nCristina Butucea (Université Paris-Est Marne-la-Vallée)\n Stanislav Minsker (University of Southern California)\nChristophe Pouet   (École Centrale de Marseille)\nVladimir Spokoiny (Humboldt University of Berlin)\n\n\n\n\n\n\n \n\n\n\n\n\n\n\n\n\nDescription\nContemporary ma chine learning algorithms define the state of the art in diverse areas (co mputer vision\, robotics and speech recognition\, to name a few)\, but in many cases theoretical justification behind the success of these methods i s still missing. Mathematical results\, in particular statistical and prob abilistic properties\, are being actively developed\, but many challenges still remain. Deep learning and generative models are particular examples of the areas with significant gaps between the engineering success and the oretical understanding. To fill this gap\, tools from diverse areas such a s nonparametric statistics\, approximation theory\, empirical process theo ry and computational efficiency are needed. This conference aims at establ ishing new fruitful collaborations among the experts in nonparametric stat istics and theoretical computer science. Expected outcome of such collabor ations are new developments in the theory of machine learning\, including the topics such as deep learning\, robustness\, privacy and estimation und er fairness constraints.\n\nLectures\nPeter Bartlett (UC Berkeley)   Be nign overfitting and adversarial examples  (abstract)\nGabor Lugosi (Pom peu Fabra University\, Barcelona)  Network archeology: a few results and questions  (abstract)\n\nTalks\nArya Akhavan (Iit - Ensae)   Distribute d Zero-Order Optimization under Adversarial Noise\nRandolf Altmeyer (Unive rsity of Cambridge)   Statistical and computational guarantees for sampli ng from high dimensional posterior distributions\nDenis Belomestny (Univer sity Of Duisburg)   Rates of convergence for density estimation with gene rative adversarial networks\nAnnika Betken (University Of Twente)  Combin ing rank statistics and subsampling for a solution to the change-point pro blem in time series analysis\nGilles Blanchard (Université Paris-Saclay)   Fast rates for prediction with limited expert advice\nTimothy Cannings (University Of Edinburgh)   Adaptive Transfer Learning\nArnak Dalalyan (C rest-Ensae)   Statistical guarantees for generative models\nFarida Enikee va (Université De Poitiers)   Change-Point Detection in Dynamic Network s with Missing Links\nSubhodh Kotekal (University Of Chicago)   Minimax rates for sparse signal detection under correlation\nMatthias Löffler (Et h Zürich)   AdaBoost and robust one-bit compressed sensing\nBéatrice La urent-Bonneau (Insa De Toulouse)   Aggregated tests of independence based on HSIC measures\nTengyuan Liang (University Of Chicago)   Universal Pre diction Band\, Semi-Definite Programming and Variance Interpolation\nArsha k Minasyan (Crest-Ensae)   All-In-One Robust Estimator of the Gaussian Me an \nMohamed Ndaoud (Essec)  Minimax Supervised Clustering in the Anisot ropic Gaussian Mixture Model: A new take on Robust Interpolation\nVianney Perchet (Ensae &\; Criteo AI Lab)   Active learning and/or online sig n identification\nKolyan Ray (Imperial College London)   Bayesian inferen ce for multi-dimensional diffusions\nMarkus Reiß (Humboldt University Ber lin)   Inference on the maximal rank of time-varying covariance matrices using high-frequency data\nLionel Riou-Durand (University Of Warwick)   M etropolis Adjusted Underdamped Langevin Trajectories\nEtienne Roquain (Sor bonne Université)   Some transition boundaries for multiple testing wi th unknown null distribution\nRichard Samworth (University Of Cambridge)   Optimal subgroup selection\nGeorge Stepaniants (Massachusetts Institute Of Technology Learning)   Partial Differential Equations in Reproducing Kernel Hilbert Spaces\nBotond Tibor Szabo (Bocconi University) Optimal dis tributed testing under communication constraints in high-dimensional and n onparametric Gaussian white noise model\nMathias Trabs (Karlsruhe Institut e Of Technology)   Dispersal density estimation across scales\nNikita Zhi votovskiy (Eth)   Stability and Generalization: Some recent results\n CATEGORIES:Colloque END:VEVENT BEGIN:VTIMEZONE TZID:Europe/Paris X-LIC-LOCATION:Europe/Paris BEGIN:STANDARD DTSTART:20211031T020000 TZOFFSETFROM:+0200 TZOFFSETTO:+0100 TZNAME:CET END:STANDARD END:VTIMEZONE END:VCALENDAR