I am fortunate to be working in the Probabilistic Learning group under Isabel Valera's supervision and lucky to work closely with Amir-Hossein Karimi. My project is on the scalability of model-agnostic counterfactual explanation generation using logic-based representations. Generating these explanations under the consequential decision-making setting imposes computationally expensive constraints (e.g. heterogeneous data, causal relations among features, etc.) which require crafted algorithms w.r.t. structural properties of the problem.
Our goal is to understand the principles of Perception, Action and Learning in autonomous systems that successfully interact with complex environments and to use this understanding to design future systems