École d’été 2025

7-10 septembre 2025

Eva Cantoni

Prof. Eva Cantoni, Université de Genève et Prof. Christian Mazza, Université de Fribourg

Mme Caroline Gillardin, coordinatrice CUSO

Co organisation avec l'EPFL

Prof. Jamal Najim, Université Gustave Eiffel, France

Dr Hélène Ruffieux, University of Cambridge, UK

Prof. Johanna Ziegel, ETH Zurich, Suisse

Dr Hélène Ruffieux, University of Cambridge, UK

Title : Shrinkage and information borrowing in Bayesian hierarchical models for genetic association problems

Absract : This course introduces Bayesian hierarchical modelling approaches used in modern genetic research, with a focus on shrinkage priors and information borrowing across biological structures. We begin with a brief overview of genetic association studies, outlining their goals, data characteristics and the statistical questions posed by high dimensionality and biological complexity. A recurring theme is the correlation among nearby genetic variants, which complicates multiplicity control and can lead to spurious associations in conventional single-variable analyses. We highlight how sparse priors mitigate this by -inducing principled penalties that facilitate the discovery of weak effects genome-wide, while at the scale of local genomic regions, Bayesian model selection strategies help resolve signals in the presence of high correlation. We then explore how hierarchical models can flexibly encode domain knowledge and account for complex dependencies, while coherently quantifying uncertainty. Special attention is given to the implications of different hierarchical formulations for applied research, particularly through comparing global-local shrinkage priors, mixture priors, and variants thereof. We also discuss how Bayesian models provide a principled framework to infer global properties, such as sparsity, heritability, polygenicity and cross-context heterogeneity. The course is grounded in examples from genetic association studies. Throughout, we highlight emerging challenges and opportunities brought by advances in molecular profiling technologies and the new statistical problems they raise.

Prof. Jamal Najim, Université Gustave Eiffel, France

Title : An introduction to Large Random Matrices and some applications

Abstract: We will first present classical random matrix models. We will then describe their limiting spectrum, as the dimension goes to infinity, and state the main theorems of the theory (Wigner's theorem, Marchenko-Pastur's theorem, the circular law, etc.). We will introduce spiked models, which are important in (statistical) applications, and show how a finite-rank perturbation of a given random matrix may have asymptotic consequences on the spectrum. If time permits, we will introduce and analyze some dynamical systems based on large random matrices (Lotka-Volterra) and useful in theoretical ecology.

Prof. Johanna Ziegel, ETH Zurich, Suisse

Title : Statistical forecast evaluation

Absract:

Lecture 1: Calibration of predictions.

Predictions for uncertain future outcomes should be calibrated in the sense that predicted probabilities for future events align with observed event frequencies. Probabilistic predictions take the form of probability distributions over all possible values of the future outcome. If the future outcome is binary, there is a broadly agreed notion of calibration for probabilistic predictions. However, if the future outcome is more general, such as real-valued or multivariate, there are many notions of calibration that have been proposed and are considered in forecast evaluation. Different notions of calibration will be reviewed alongside methodology to empirically assess calibration. Furthermore, we discuss how conformal prediction techniques allow to enforce calibration out-of-sample.

Lecture 2: Proper scoring rules.

Proper scoring rules have been a subject of growing interest in recent years, not only as tools for evaluation of probabilistic forecasts but also as methods for estimating probability distributions. We review the mathematical foundations of proper scoring rules including general characterisation results and important families of scoring rules. We comment on their role in statistics and machine learning for estimation and forecast evaluation. Furthermore, the connection of calibration to proper scoring rules will be discussed.

Lecture 3: Point predictions and elicitability.

Point predictions do not quantify the uncertainty of future outcomes comprehensively but they may be required for pricing, reporting, decision making, communication or simply tradition. Calibration can also be defined for point predictions and we will review possibilities for empirical calibration assessment. Point predictions should be compared with consistent scoring functions. We will define elicitable functionals and see that only predictions for elicitable functionals allow for meaningful comparisons of predictive performance.

Welcome tea Sunday : Hôtel Eden

Apero Sunday : Bar Hôtel Eden

Breakfast, lunch and dinner : Hôtel Eden

This program may be changed

Anzère- Eden Resort - Alpes valaisannes

Hôtel : Eden Resort Anzère

Adress : Route d'Anzère 34, 1972 Anzère, Canton du Valais

Tel +41 (0)27 399 31 00 L'hôtel est situé dans les Alpes valaisannes. Il y a des chambres et des suites.

Accès à Anzère en voiture: Google Map

EN AVION Aéroports internationaux de: - Genève (180 km) - Zürich (290 km) - Bâle (270 km)

En transport public Horaires Swiss Train :

De: Aéroport de Genève : Train jusqu'à Sion. A la gare de Sion : car postal Sion - Anzère centre (36 mns)

Swiss Train schedule : From: Geneva airport, To: Sion. From Sion station : postal bus to Anzère centre. Travel time: Genève - Sion (1 hour and 55 minutes); Sion - Anzère (36 minutes).

Visa pour la Suisse (demande de visa suisse en ligne)

Météo en suisse (meteoswiss.admin.ch)

Tarif :

CUSO (UNINE, UNIGE, UNIL, UNIFR, UNIBE, IHEID, HES-SO)

Doctorant-e CUSO appartement en chambre double avec salle de bains partagée: 200 CHF

Doctorant-e CUSO appartement en chambre simple avec salle de bains partagée: 325 CHF

Doctorant-e CUSO studio privé avec salle de bains privée: 350 CHF

Post-doctorant-e CUSO appartement en chambre double avec salle de bains partagée: 300 CHF

Post-doctorant-e CUSO appartement en chambre simple avec salle de bains partagée: 375 CHF

Post-doctorant-e CUSO studio privé avec salle de bains privée: 450 CHF

Professeur-e CUSO appartement en chambre double avec salle de bains partagée : 400 CHF

Professeur-e CUSO appartement en chambre simple avec salle de bains partagée : 475 CHF

Professeur-e CUSO studio privé avec salle de bains privée: 550 CHF

Non CUSO appartement en chambre double avec salle de bains partagée: 1000 CHF

Non CUSO appartement en chambre simple avec salle de bains partagée: 1100 CHF

Non CUSO studio privé avec salle de bains privée: 1200 CHF

Lors de votre inscription, merci de bien vouloir indiquer dans la zone commentaire si vous désirez un studio, 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, un studio privé sera réservé. Si vous vous inscrivez et que vous ne pouvez pas participer, veuillez nous contacter dès que possible. Dans le cas contraire, toutes les nuits d'hôtel pourraient vous être facturées.

*Condition d'annulation :

Pour une annulation effectuée entre la date de réservation et 30 jours avant l'arrivée aucun frais d'annulation ne sera prélevé.Pour une annulation effectuée entre 7 et 30 jours avant l'arrivée un montant équivalent à 30 % de la réservation sera prélevé.Pour une annulation effectuée entre 7 jours avant l'arrivée et le jour de l'arrivée la totalité de la réservation sera prélevée. Pour une annulation effectuée entre le jour de l'arrivée et le no show la totalité de la réservation sera prélevé. Pour cause d'accident ou maladie, etc, merci de nous livrer un certificat médical.

*Cancellation policy:
For cancellations made between the reservation date and 30 days before arrival, no cancellation fee will be charged.
For cancellations made between 7 and 30 days before arrival, an amount equivalent to 30% of the reservation will be charged.
For cancellations made between 7 days and the day of arrival, the full amount of the reservation will be charged.
For cancellations made between the day of arrival and no-show, the full amount of the reservation will be charged.
In the event of accident or illness, etc, please provide a medical certificate.

Versement sur compte postal (payment into postal account) :

CUSO
CCP 12-1873-8
Neuchâtel
BIC : POFICHBEXXX
IBAN : CH0509000000120018738. Merci d'écrire votre nom suivi du no" 25220002 " lors du paiement. Thank you to write your name on the payment wording and nb" 25220002".

30