I am Staff Research Scientist in Machine Learning at DeepMind.
I received a Diploma di Laurea in Mathematics from
University of Bologna
and a PhD in Machine Learning from École Polytechnique Fédérale de Lausanne (IDIAP Research Institute).
Before joining DeepMind I worked in
the Empirical Inference Department
at the Max-Planck Institute for Intelligent Systems (Prof. Dr. Bernhard Schölkopf),
in the Machine Intelligence and Perception Group at
Microsoft Research Cambridge
(Prof. Christopher Bishop)
and the Statistical Laboratory, University of Cambridge (Prof. Philip Dawid).
My research interests are based around Bayesian & causal reasoning, graphical models, variational inference,
time-series models, deep learning, and ML fairness and bias.
I am looking for a research scientit with background in Bayesian reasoning. Please contact me if interested.
Wasserstein fair classification. R. Jiang, A. Pacchiano, T. Stepleton, H. Jiang, and S. Chiappa, UAI 2019.
Unsupervised separation of dynamics from pixels. S. Chiappa and U. Paquet, METRON,
Special Issue on Hidden Markov Models, Springer 2019.
Meta-learning of sequential strategies. P. Ortega et al. 2019.
A causal Bayesian networks viewpoint on fairness. S. Chiappa and William S. Isaac.
Privacy and Identity Management.
Fairness, Accountability, and Transparency in the Age of Big Data.
E. Kosta et al. Editors, Springer Nature Switzerland, IFIP AICT 547, pages 3–20, 2019.
Degenerate feedback loops in recommender systems. R. Jiang, S. Chiappa, T. Lattimore, A. György, and P. Kohli.
ACM Conference on AI, Ethics, and Society, 2019. arXiv:1902.10730
Path-specific counterfactual fairness. S. Chiappa. AAAI-2019.
Causal reasoning from meta-reinforcement learning. I. Dasgupta, J. Wang,
S. Chiappa, J. Mitrovic, P. Ortega, D. Raposo, E. Hughes, P. Battaglia, M. Botvinick, and Z. Kurth-Nelson, 2019.
Comparing interpretable inference models for videos of physical motion. M. Pearce, S. Chiappa, and U. Paquet.
Jan Leike and myself gave the ICML 2019 tutorial
Safe Machine Learning.
The recording is available at SlidesLive.
I co-organized the ICLR 2019 Workshop
Safe Machine Learning: Specification, Robustness, and Assurance.
The recordings is available at
I will be Program Chair of AISTATS 2020.