Towards Reliable Machine Learning: Transfer & Physics Informed Learning, and Conformal Prediction, ECAS-SFdS course, Fréjus (France), December, 1–5, 2025

1st Dec 2024

Towards Reliable Machine Learning: Transfer & Physics Informed Learning, and Conformal Prediction.

December 1-5, 2025 – La Villa Clythia – CAES du CNRS, Fréjus

The next ECAS-SFdS school will take place from December 1 to 5, 2025, on the French Riviera and will focus on reliable machine learning through two different approaches: transfer & physics-informed learning and conformal prediction. The first aims to leverage diverse knowledge to implement efficient models with an economy of data, addressing the critical challenge of domain shift between the training distribution and the distribution of data on which the model is used, while the second is a versatile statistical technique for distribution-free, finite-sample, post-hoc uncertainty quantification that associates prediction sets from any prediction model. The course will be taught in English and will start with the basics and end with the most recent and advanced methods like conformal prediction for time series. Methodological aspects will be covered as well as applied and computational aspects.
The registration is open.

More information on this webpage