Causality of Enhanced Model Interpretability

Amir-Hossein Karimi (Ph.D. Student)

As machine learning is increasingly used to inform decision-making in consequential real-world settings (e.g., pre-trial bail, loan approval, or prescribing life-altering medication), it becomes important to explain how the system arrived at its decision, and also suggest actions to achieve a favorable decision. My thesis objective is to study, design, and deploy methods to address the second question, specifically on generating counterfactual explanations (https://arxiv.org/abs/1905.11190) and minimal interventions (https://arxiv.org/abs/2002.06278). Thus my focus is on the intersection of machine learning interpretability, causal and probabilistic modelling, and social philosophy and psychology.

Primary Host:	Bernhard Schölkopf (ELLIS Institute Tübingen & Max Planck Institute for Intelligent Systems)
Exchange Host:	Thomas Hofmann (ETH Zürich)
PhD Duration:	01 October 2018 - 31 December 2022
Exchange Duration:	01 September 2020 - 31 August 2021 - Ongoing