Center for Advanced Intelligence Project

Join Zoom Meeting
https://riken-jp.zoom.us/j/9456523132?pwd=SVVvMDNCM0JJL2hUWi8rL0NQWUlydz09

Meeting ID: 945 652 3132
Passcode: 117764

Title: Automating Probabilistic Reasoning and Learning
Abstract: Probabilistic reasoning is the ideal candidate to enable and foster the trustworthy deployment and execution of artificial intelligence (AI) and machine learning (ML) systems as it al-
lows to inspect a system’s behavior at deployment time in the presence of uncertainty. Unfortunately,probabilistic reasoning is actually often a bottleneck rather than an enabler, as there is no systematic way to efficiently and reliably reason about the different complex behaviors of the many ML models already deployed. At the same time, ML and AI practitioners have no principled and general methodology to design reliable ML models ex novo. In this talk, I will show a theoretical framework under which different ML formalisms can be abstracted in a unified computational representation: circuits. By doing so we can decompose the task of reasoning over the behavior of ML systems into smaller modular primitives over these circuits that can be proved to be exact, thus automatically guaranteeing efficient and reliable complex reasoning by design. Finally I will discuss what is missing into making this a practical toolchain for everyday probabilistic reasoning.

Bio:
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 unifying and 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, supervised by Isabel Valera. 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.