CSE Colloquium: From Simple Inference to Complex Probabilistic Reasoning

Zoom Information: Join from PC, Mac, Linux, iOS or Android: https://psu.zoom.us/j/97522392875?pwd=aXpHS1ozZmdBOVlzK3Fwak9hT2daUT09 Password: 665166 

Or iPhone one-tap (US Toll): +13126266799,97522392875# or +16468769923,97522392875# 

Or Telephone: Dial: +1 312 626 6799 (US Toll) +1 646 876 9923 (US Toll) +1 301 715 8592 (US Toll) +1 346 248 7799 (US Toll) +1 669 900 6833 (US Toll) +1 253 215 8782 (US Toll) Meeting ID: 975 2239 2875 Password: 665166 International numbers available: https://psu.zoom.us/u/acSCXLWbss 

ABSTRACT: Probabilistic reasoning is generally considered to be the framework-of-choice to enable and support decision making under uncertainty in real-world scenarios. Ideally, we would like a probabilistic ML system that is deployed in the wild to be able to i) allow humans (or other AI agents) to pose arbitrary and articulated queries, that is questions about states of the world; ii) to provide guarantees on their results; iii) to deal with complex, heterogeneous and potentially structured data and, moreover iv) to support chaining several inference steps together. In this talk, I will argue that the above desiderata are still unmet in the current landscape of probabilistic ML. Even the most prominent paradigm nowadays, deep generative modeling, is able to provide only a shallow, simplistic, form of inference and struggles when dealing with complex queries or data. I will then delineate how my past and current research aimed at closing this gap. Specifically, I will touch some recent works investigating principled frameworks within dealing with complex tasks such as reasoning about the behavior of classifiers or dealing with algebraic constraints over heterogeneous data can be done elegantly and efficiently. Lastly, I will talk about some future research perspectives: extending these complex probabilistic reasoning routines to interactive and relational settings while allowing for approximations with guarantees. 

BIOGRAPHY: Antonio Vergari is currently a postdoc in the StarAI Lab lead by Guy Van den Broeck at UCLA working on advanced probabilistic reasoning and learning on deep representations. Previously, he did a postdoc at the MPI-IS in Tuebingen where he worked with Isabel Valera on automating machine learning via tractable probabilistic models. He obtained a PhD in Computer Science and Mathematics at the University of Bari, Italy. He organized the Tractable Probabilistic Modeling Workshop at ICML2019, the Tractable Probabilistic Inference Meeting (T-PRIME) at NeurIPS 2019 and presented a series of tutorials on modern probabilistic reasoning and models at UAI 2019, AAAI 2020, ECAI 2020. He will organize a Dagsthul Seminar on "New Trends in Tractable Probabilistic Inference" in 2022 with Prof. Kristian Kersting and Prof. Max Welling.