Professor Imbens also had a mentoring session with our PhD students actively working on causality, discussing their ideas and the potential impact of their applications! 👨‍🔬👩‍🔬

@matyasch.bsky.social @roelhulsman.bsky.social @rmassidda.it @danruxu.bsky.social 🔥

📝👥 Joint work with a group of great researchers @Dingling_Yao @seblachap @PerouzT @JKugelgen @FrancescoLocat8 @saramagliacane

3️⃣Finally, we propose two methods that implement these theoretical results and validate their effectiveness with experiments on simulated data and image benchmarks.

2️⃣We introduce two theoretical results for identifying causal variables up to permutation and element-wise transformation under partial observability. Both results leverage a sparsity constraint.

1️⃣ We formalize the Unpaired Partial Observations setting for causal representation learning, where each partial observation captures only a subset of causal variables.

☀️ ICML2024 ☀️

Tuesday 11:30-13:00 #2201

❓Do you want to identify high-level causal variables from perceptual data under partial observable setup?

💡Here we focus on learning from unpaired observations from a dataset with an instance-dependent partial observability pattern.