Information détaillée concernant le cours
| Titre | École d’hiver 2020 |
|||||||||||||||||||||||||||||||||||||||
| Dates | 2 - 5 février 2020 |
|||||||||||||||||||||||||||||||||||||||
| Responsable de l'activité | Sebastian Engelke |
|||||||||||||||||||||||||||||||||||||||
| Organisateur(s)/trice(s) | Sebastian Engelke, UNIGE (Président); Yves Tillé, UNINE (Vice-président); Caroline Gillardin, UNINE (coordinatrice)
|
|||||||||||||||||||||||||||||||||||||||
| Intervenant-e-s | Prof. Michael Bronstein (Imperial College London (Workshop GeoCow-Sunday 2 Feb.)) Prof. Sylvia Frühwirth-Schnatter (Vienna University of Economics and Business) Prof. Johan Segers (Université Catholique de Louvain) |
|||||||||||||||||||||||||||||||||||||||
| Description | Prof. Michael Bronstein (Imperial College London)
Title : Minicourse on Deep Learning on Graphs and Manifolds - Numerical computation for statistics
Workshop GeoCow-Sunday 2 February- 11AM-5PM- salle du centre de conférence de la commune. (https://sites.google.com/view/geocow2020/home). The first part of the event consists in a 1-day minicourse on deep learning on graphs and manifolds, designed as an introduction for students, young researchers, as well any interested participant.
Voici un lien vers un dossier contenant les documents que Michael Bronstein va utiliser dimanche durant ses 2 interventions : https://drive.google.com/open?id=1S1HM_6sGJ82Fi9vTuT2hks4mxTFWBwXg
Pour la partie « Sandbox », Michael Bronstein a fourni les liens suivants :
GCN - simplest graph neural net: https://docs.dgl.ai/en/latest/tutorials/models/1_gnn/1_gcn.html
GAT: https://docs.dgl.ai/en/latest/tutorials/models/1_gnn/9_gat.html
En soutien pour les débutants, Isaline et Xavier (UNIFR) vont se baser sur le contenu suivant : https://docs.dgl.ai/en/latest/index.html et essentiellement être disponibles pour les parties « Installation » et « DGL at Glance » (dans la section « Get started »). Michael Bronstein sera en principe aussi présent à la session « Sandbox » ; il a fourni toutes ces infos (docs+liens) afin que nous puissions vous les transmettre en avance.
Prof. Sylvia Frühwirth-Schnatter (Vienna University of Economics and Business)
Title : Finite Mixture and Markov Switching Models - The Bayesian perspective
Finite mixture models and their extensions to mixture of experts and Markov switching models are very popular in analysing data of multiple kinds. These models are useful for flexible modelling, density estimation and unsupervised clustering both in statistics and econometrics. The course consists of three lectures that discuss mixture models from a Bayesian perspective. The first lecture provides an introduction to finite mixture models and discusses statistical inference for mixtures with a known number of components using Markov chain Monte Carlo methods. The second lecture addresses the challenging problem of choosing the number of components for finite mixture and discusses methods such as marginal likelihoods and sparse finite mixtures. Special emphasis will be put on the difference between estimating the number of components and the number of clusters in the unknown partition. The third lecture discusses two main extensions of finite mixtures, namely mixtures-of-experts models and Markov switching models. Throughout all lectures, applications to several benchmark data sets example will be provided for illustration. The course concludes with an exercise session.
Prof. Johan Segers (Université Catholique de Louvain)
Title : "Empirical Processes with Applications in Statistics"
The title of the course is shamelessly paraphrased from the great book from 1996 by A.W. van der Vaart and J.A. Wellner, upon which this lecture series is heavily inspired. After lying the groundwork of the Hoffmann-Jorgensen theory of weak convergence of bounded stochastic processes, we will study functional laws of large numbers and functional central limit theorems for stochastic processes that arise when sample averages are computed for an infinite family of functions. The convergence mode is sufficiently strong to exert control over the whole trajectory of the process. Having such a firm grip is crucial for establishing limit distributions of estimators and test statistics that arise as suprema, integrals, maximisers, inverses, or other functionals applied to the empirical process. The teacher's predilections will shine through via illustrations from classical and recent advances in copula theory and extreme value analysis. Master the great tool of empirical processes, and no sequence of statistics will be safe from your analysis anymore.
Program
|
|||||||||||||||||||||||||||||||||||||||
| Lieu |
Les Diablerets (VD) |
|||||||||||||||||||||||||||||||||||||||
| Information |
www.eurotel-victoria.ch/diablerets/
Accès aux Diablerets :
EN VOITURE Autoroute A9, direction Grand St-Bernard, sortie Aigle. Puis la route Aigle - Les Diablerets - Col du Pillon (20km).
EN AVION Aéroports internationaux de: - Genève (120 km) - Zürich (250 km) - Bâle (200 km)
EN TRAIN (HORAIRE DES TRAINS - RAILWAY TIMETABLE) International TGV Paris - Lausanne. En hiver, TGV des Neiges Paris - Lausanne - Aigle.
Swiss Train schedule : From: Geneva airport, To: Les Diablerets, gare. Trains directs jusqu'à Aigle. Ensuite train de montagne A.S.D (Aigle - Sépey - Diablerets) Durée des trajets: Lausanne - Aigle (30 minutes), Aigle - Les Diablerets (50 minutes).
Visa pour la Suisse (Swiss Online Visa application)
Météo en suisse (meteoswiss.admin.ch)
Adresse salle de gym Maison des congrès : Chemin des Grandes Isles, 1865 Ormont-Dessus (Entre la gare les Diableret et l'Eurotel)
|
|||||||||||||||||||||||||||||||||||||||
| Frais | Doctorant CUSO chambre double: 200 CHF Doctorant CUSO chambre simple: 350 CHF Post-doctorant CUSO chambre double: 300 CHF Post-doctorant CUSO chambre simple: 450 CHF Professeur CUSO chambre double: 400 CHF Professeur CUSO chambre simple: 550 CHF Non CUSO universitaire chambre double: 850 CHF Non CUSO universitaire chambre simple: 1000 CHF Non CUSO privé chambre double: 1300 CHF Non CUSO privé chambre simple: 1500 CHF
Lors de votre inscription, merci de bien vouloir indiquer dans la zone commentaire si vous désirez une chambre simple, ou double et le nom de la personne avec qui vous souhaiteriez partager votre chambre. Dans le cas où rien n'est indiqué, une chambre simple sera réservée.
|
|||||||||||||||||||||||||||||||||||||||
| Inscription | Versement sur compte postal:
CUSO CCP 12-1873-8 Neuchâtel BIC : POFICHBEXXX IBAN : CH0509000000120018738.
Merci d'écrire votre nom lors du paiement. Thank you to write your name on the payment wording.
|
|||||||||||||||||||||||||||||||||||||||
| Places | 50 |
|||||||||||||||||||||||||||||||||||||||
| Délai d'inscription | 28.01.2020 |
short URL
URL onepage