This workshop is part of the Bernoulli Center programme at EPFL and will take place from 23 to 24 February 2026. Please note it will not be held at the Bernoulli Center, but instead at the IC Faculty.

In recent years, information-theoretic and statistical tools have led to new breakthroughs in various areas of machine learning. Examples include community detection, learning under information constraints, distributed learning, generalization guarantees, compression, Wasserstein GANs and diffusion models. The workshop aims to identify such themes and investigate potential new topics where information-theoretic tools can lead to fundamentally new advancements.