Autumn school in Bayesian Statistics 2023

Research school

30th October - 3rd November 2023, CIRM, Marseille

The objective of this autumn school is to provide a comprehensive overview of Bayesian methods for complex settings: modelling techniques, computational advances, theoretical guarantees and practical implementation. It will include two masterclasses, on Sequential Monte Carlo and on Bayesian causal inference, tutorials on NIMBLE and on Bayesian Statistics with Python, and a selection of invited and contributed talks.

Speakers

2 Master classes (2 x 2h each) 2 tutorials (2h each) and 6 invited speakers (1h each)

Master classes

Avatar

Nicolas Chopin

Professor of Data Science, ENSAE, Institut Polytechnique de Paris.

Avatar

Silvia Chiappa

Research Scientist at Google DeepMind

Tutorials

Avatar

Gabriel Victorino Cardoso

PhD candidate in statistics at Télécom SudParis - Ecole Poytechnique and IHU-Liryc

Avatar

Yazid Janati El Idrissi

PhD candidate in statistics at Télécom SudParis - Institut Polytechnique de Paris,

Invited speakers

Avatar

Fabrizia Mealli

Director of the Florence Center for Data Science, University of Florence.

Avatar

François Caron

Professor in the department of Statistics and Tutorial Fellow at Keble College, University of Oxford

Avatar

Jean-Michel Marin

Professor of Statistics and Dean of the Faculty of Sciences of Montpellier France

Avatar

Marta Catalano

Harrison Early Career Assistant Professor in the Department of Statistics at the University of Warwick.

Avatar

Sophie Donnet

Senior researcher at INRAE and vice Head of MIA Paris Saclay,

Avatar

Sylvain Le Corff

Professor in LPSM, Sorbonne Université.

Information

Registrations are closed.

There is no registration fee. Room and board are available for all participants, and should be paid directly to CIRM (you should have received information about this step). The organizers have secured funding to cover the room and board costs of a number of participants, but the application deadline has passed and all funded participants have been contacted.

Abstracts for the talks and posters are available here.

Detailed program

A good start on Monday

Speaker Title
8:45-9:00 Introduction Organizers Opening remarks
9:00-11:00 Master Class Nicolas Chopin An introduction to state-space models, particle filters, and Sequential Monte Carlo samplers
11:00-11:30 Social event Coffee Break
11:30-12:30 Invited talk Marta Catalano Merging rate of opinions via optimal transport on random measures
12:30-14:00 Social event Lunch
14:00-16:00 Tutorial Gabriel Victorino Cardoso and Yazid Janati El Idrissi Leveraging JAX for Bayesian Inference
16:00-16:30 Social event Coffee Break
16:30-17:00 Contributed Liam Llamazares Penalized complexity priors for stochastic partial differential equations
17:00-17:30 Contributed Joshua Bon Bayesian score calibration for approximate models
17:30-19:30 Poster session
19:30-21:00 Social event Dinner

A natural continuation on Tuesday

Speaker Title
9:00-11:00 Master Class Nicolas Chopin An introduction to state-space models, particle filters, and Sequential Monte Carlo samplers
11:00-11:30 Social event Coffee Break
11:30-12:00 Contributed David Agnoletto Bayesian inference for generalized linear models via quasi-posteriors
12:00-12:30 Contributed Elena Bortolato Coupling MCMC algorithms on submanifolds
12:30-14:00 Social event Lunch
14:00-15:00 Invited talk Sylvain Le Corff Monte Carlo guided Diffusion for Bayesian linear inverse problems
15:00-15:30 Contributed Francesca Crucinio Optimal Scaling Results for a Wide Class of Proximal MALA Algorithms
15:30-16:00 Contributed Filippo Ascolani Complexity of Gibbs samplers through Bayesian asymptotics
16:00-16:30 Social event Coffee Break
16:30-17:30 Invited talk Jean-Michel Marin Goodness of Fit for Bayesian Generative Models
18:00-19:00 Social event Football game
19:30-21:00 Social event Dinner

The perfect balance on Wednesday

Speaker Title
9:00-11:00 Master Class Silvia Chiappa Graph-based Statistical Causality
11:00-11:30 Social event Coffee Break
11:30-12:00 Contributed Jacopo Iollo Tempered sequential Monte Carlo for Bayesian experimental design via stochastic optimization
12:00-12:30 Contributed Mengyan Zhang Bayesian optimisation with aggregated feedback
12:30-14:00 Social event Lunch
14:00-19:30 Social event Free time
19:30-21:00 Social event Dinner
21:00-22:30 Social event Pub Quizz

Without weakening on Thursday

Speaker Title
9:00-11:00 Master Class Silvia Chiappa Silvia Chiappa
11:00-11:30 Social event Coffee Break
11:30-12:00 Contributed Pierre Gloaguen Structured variational inference for hidden Markov models
12:00-12:30 Contributed Thibaut Lemoine Monte Carlo integration on complex manifolds
12:30-14:00 Social event Lunch
14:00-16:00 Tutorial Gabriel Victorino Cardoso and Yazid Janati El Idrissi Leveraging JAX for Bayesian Inference
16:00-16:30 Social event Coffee Break
16:30-17:30 Invited talk Fabrizia Mealli Bayesian Causal Inference: A Potential Outcome Perspective with Applications to Intermediate Variables
19:30-21:00 Social event Bouillabaisse
21:00-23:00 Social event Karaoke night

One more for the road on Friday

Speaker Title
9:00-10:00 Invited talk Sophie Donnet Using a Sequential Monte Carlo algorithm to find the mesoscale structure of a network
10:00-10:30 Contributed Anna Menacher Scalar-on-image regression with a relaxed Gaussian process prior
10:30-11:00 Contributed Claudio del Sole Hierarchically dependent mixture hazard rates for modelling competing risks
11:00-11:30 Social event Coffee Break
11:30-12:00 Contributed Felipe Uribe Towards dimension reduction of Bayesian inverse problems with neural network priors
12:00-12:30 Introduction Organizers Closing remarks
12:30-14:00 Social event Lunch

Sponsors

SFdS

Committees