Simulation-based inference with Swyft

Europe/Amsterdam
B0.203 (University of Amsterdam)

B0.203

University of Amsterdam

Science Park 904 1098XH Amsterdam
Christoph Weniger (University of Amsterdam), James Alvey (University of Amsterdam), Noemi Anau Montel (GRAPPA)
Description

Objective

The goal of this in-person workshop is to make progress in tackling the most difficult* parameter inference problems using state-of-the-art simulation-based inference techniques as implemented in Swyft**.

*Difficult = slow simulator/model; dozens, thousands or millions of parameters; complex posterior; unknown optimal summary statistics; ...

**Swyft is a pytorch-lightning-based implementation of truncated marginal neural ratio estimation (TMNRE), which is now successfully used for a diverse set of inference problems.

 

Swyft in action

Further information

The workshop is planned to be in-person. If you are interested to join online, please let us know. Depending on demand, we might change part of the workshop to a hybrid version.


 

Participants
  • Alejandra Aguirre-Santaella
  • Alessandro Morandini
  • Alex Cole
  • Alexandra Wernersson
  • Androniki Dimitriou
  • Benjamin Miller
  • Camila Correa
  • Christoph Weniger
  • Christopher Eckner
  • Cristina Fernández Suárez
  • Ebo Peerbooms
  • Fabian Zimmer
  • Florian List
  • Gianfranco Bertone
  • Guadalupe Cañas-Herrera
  • Guillermo Franco Abellán
  • James Alvey
  • Joanna Berteaud
  • Karel Geraedts
  • Kilian Scheutwinkel
  • Konstantinos Leontaridis
  • Kosio Karchev
  • Martín De los Rios
  • Maryam Tajalli
  • Mathis Gerdes
  • Matteo Martinelli
  • Noemi Anau Montel
  • Oleg Savchenko
  • Oliver Böhler
  • Oscar Macias
  • Roberto Caiozzo
  • Roberto Ruiz de Austri
  • Samuel Lange
  • Sebastian Hoof
  • Sheridan Lloyd
  • Shin'ichiro Ando
  • Sibilla Bouché
  • Spyridon Markesinis
  • Stéphane Ilic
  • Theophanes Karydas
  • Thomas Edwards
  • Uddipta Bhardwaj
  • Will Handley
  • Youyou Li