Date : 2023-11-27 => 2023-12-01
Lieu : Institut d’Astrophysique de Paris, Paris, France

Abstract deadline: August 31st 2023, Registration deadline please see note below

Machine learning techniques are developing rapidly. After our highly successful 2021 meeting, “Machine Learning for astronomical surveys”, an avalanche of new data and an ever-growing use of ML in astronomical surveys clearly mandated a follow-up.

This year’s meeting follows the same format as previously: a series of invited summary talks, short and very lively contributed talks, posters and debates. Our aim is the same as before: to cast a critical eye on the application of machine-learning techniques in astronomical surveys, including field-level inference, likelihood free approaches, generative models.

The need for new data-analysis techniques for next-generation surveys is no longer in doubt, but the applicability of these techniques (often developed outside of astronomy) needs to be questioned more than ever. We aim to make this conference a forum for discussions on problems
and solutions in data analysis of astronomical surveys. We are also interested in emerging class of problems in astronomy that mandate an evolution of our data analysis techniques.

This time, to bring together as many people as possible, while limiting our carbon impact, this conference will be organised in two locations simultaneously, at the IAP in Paris and the Flatiron Institute in New York, with speakers and audiences at both sites. A professional production company will provide high-resolution live streaming video.

While the main conference and debates will be held simultaneously (in the afternoon in Paris and in the morning in NY), the time-shifted period (morning in Paris and afternoon in NY) will be devoted to in depth review talks by leading experts in the field including:

• Miles Cranmer (Cambridge University)
• Marylou Gabrié (CMAP, Polytechnique)
• Tomasz Kacprzak (ETH Zurich)
• Jens Jasche (Stockholm University)
• Soledad Villar (JHU)
• Tiziana DiMatteo (CMU)

The conference will features three debates, organised jointly between Flatiron and IAP hosted simultaneously:

• What can machine-learning do for the next generation surveys?
• What is the impact of large language models in astronomy?
• Is there truth in latent space?

These debates will be led by experts in machine-learning and/or surveys, with a wide range of views, which will certainly lead to lively discussions, including:

• Nabila Aghanim (IAS, Orsay)
• Pierre Casenove (CNES)
• Aleksandra Ciprijanovic (Fermilab)
• Helena Domínguez Sánchez (CEFCA)
• David Hogg (NYU / Flatiron Institute)
• Kyunghyun Cho (NYU)
• François Lanusse (LCS, CEA)
• Luisa Lucie-Smith (MPA)
• Henry Joy McCracken (IAP, Sorbonne Université)
• David Spergel (Simons Foundation)
• Licia Verde (ICC-UB)
• Lawrence Saul (Flatiron Institute)
• Torsten Ensslin (MPA)

More information can be found at the conference website, please note the preliminary timetable.

Please register to the correct node that you want to attend to. Payment for the Paris node participation will only be called for by mid-September.

Registration closes for New York / Flatiron on September 30th, 2023. Abstract submission closes on August 31th 2023.

Lien direct