UNREAL, making an ERC StG real
Recently I have been lucky to be awarded an ERC Starting Grant on the topic of automating probabilistic reasoning for trustworthy machine learning (ML) models.
In this talk I will briefly describe my proposal, UNREAL and how it will deliver a theoretical and practical framework under which different ML formalisms can be abstracted in a unified computational representation: circuits. I devised UNREAL as to decompose the task of reasoning over the behavior of ML systems into smaller modular primitives over these circuits that will be provably reliable and efficient. This is in stark contrast with the direction of modern ML. I will talk about how I shaped this "paradigm shift" through a series of foundational stepping stones. I will reflect on the efforts given to put the pieces together and about how luck can play a role in this scenario.
Finally, I will link this experience with the equally challenging experience of being a PI of a research lab.
About the speaker
Antonio Vergari is a Lecturer (Assistant Professor) in Machine Learning at the University of Edinburgh. His research focuses on efficient and reliable machine learning in the wild; tractable probabilistic modeling and combining learning with complex reasoning. He recently was awarded an ERC Starting Grant on automating probabilistic reasoning for trustworthy ML. Previously he was postdoc in the StarAI Lab lead by Guy Van den Broeck at UCLA. Before that he did a postdoc at the Max Planck Institute for Intelligent Systems in Tuebingen in the Empirical Inference Department of Bernhard Schoelkopf. He obtained a PhD in Computer Science and Mathematics at the University of Bari, Italy. He likes to tease and challenge the probabilistic ML community at large on how we desperately need reliable ML an AI models nowadays. To this extent, he organized a series of tutorials, workshops, seminars and events at top ML and AI venues such as UAI, ICML, AAAI, IJCAI and NeurIPS and last year a Dagstuhl Seminar.