I work at ATHENA RC and do my PhD at HUA supervised by Christos Diou. My research is on interpretable ML systems, with two main strands: eXplainable AI, which explains black-box models [1][2] or builds x-by-design models from scratch [3], and Simulation-based Inference, which fits interpretable scientific simulators to data [4].
On SBI, and in probabilistic ML in general, I often work with Michael Gutmann.
On XAI, I often work with Giuseppe Casalicchio and the IML team led by Bernd Bischl.
I contribute to, and sometimes lead, open-source projects like Effector and ELFI.
I publish at and review for conferences like NeurIPS, AISTATS and ECML, and journals like JAI.
I believe in slow science. The current pace burns people out and buries meaningful research under an avalanche of noise.
Personal websites are great, but we don’t need more 500-pound websites.
Researching explainable-by-design models and post-hoc techniques for black-box models, with a special focus on explaining deep learning systems trained on tabular data.
There, I took two pivotal courses, MLPR (Ian Murray) and PMR (Michael Gutmann), that shaped my understanding of machine learning.
