Identifiability of latent causal variables under interventions

A theory-oriented thesis on when latent causal factors can be recovered from interventional data. This project sits within the causal inference and statistics activities of our group at Max Planck Institute for Intelligent Systems, and builds on several recent publications and ongoing collaborations with industry and other research groups.

• Review the state of the art in identifiability and formulate a precise research question
• Design and implement the methodology described above
• Evaluate results rigorously, including ablations and comparison with baselines
• Document the work in a thesis and, where results allow, a conference paper

You will join weekly group meetings, work closely with a PhD student as day-to-day supervisor, and have access to our computing/lab infrastructure. We expect independent work, curiosity and good communication. The exact scope is adapted to a phd thesis of about 12 months.

• Supervision by Clara Fischer and an experienced team
• Financial support (see funding details)
• An international environment and the possibility to continue with a PhD for strong candidates

Apply through ThesisAbroad with your CV, transcript and a short motivation explaining why this topic interests you. Shortlisted candidates are invited to a 30-minute video call.

• Enrolled in a PhD-track programme in Mathematics or a related field
• Solid background in causal inference
• English (B2 or higher)
• Programming or lab experience relevant to the topic
• Ability to spend the full duration on site