Statistical and Relational Artificial Intelligence Lab

UCLA - Computer Science Department
Engineering VI Room 368A
404 Westwood Plaza
Los Angeles, CA 90095-1596

The Statistical and Relational Artificial Intelligence (StarAI) lab is directed by Prof. Guy Van den Broeck. The StarAI lab performs research on Machine Learning (Statistical Relational Learning, Tractable Learning), Knowledge Representation and Reasoning (Graphical Models, Lifted Probabilistic Inference, Knowledge Compilation), Applications of Probabilistic Reasoning and Learning (Probabilistic Programming, Probabilistic Databases), and Artificial Intelligence in general.

Recent Publications

2021

[147], , , and . Juice: A Julia Package for Logic and Probabilistic Circuits, In Proceedings of the 35th AAAI Conference on Artificial Intelligence (Demo Track), .
[146], , , and . Noisy Variational Quantum Algorithm Simulation via Knowledge Compilation for Repeated Inference, In Architectural Support for Programming Languages and Operating Systems (ASPLOS), .

2020

[145], , , and . Probabilistic Inference with Algebraic Constraints: Theoretical Limits and Practical Approximations, In Advances in Neural Information Processing Systems 33 (NeurIPS), . Oral spotlight presentation, acceptance rate 385/9454 = 4.1%
[144], , and . Counterexample-Guided Learning of Monotonic Neural Networks, In Advances in Neural Information Processing Systems 33 (NeurIPS), .
[143], and . Group Fairness by Probabilistic Modeling with Latent Fair Decisions, In Algorithmic Fairness through the Lens of Causality and Interpretability Workshop at NeurIPS (AFCI), .
[142], , , and . On Effective Parallelization of Monte Carlo Tree Search, In Deep Reinforcement Learning Workshop at NeurIPS (DRLW), .
[141], , , , and . SAM: Squeeze-and-Mimic Networks for Conditional Visual Driving Policy Learning, In Conference on Robot Learning, .
[140], and . Scaling Exact Inference for Discrete Probabilistic Programs, In Proc. ACM Program. Lang. (OOPSLA), ACM, .  [doi] ACM SIGPLAN distinguished paper award
[139], and . Probabilistic Circuits: A Unifying Framework for Tractable Probabilistic Models, In , .
[138], and . Strudel: Learning Structured-Decomposable Probabilistic Circuits, In Proceedings of the 10th International Conference on Probabilistic Graphical Models (PGM), .

Recent Talks

TutorialMay 2020
Slides

Probabilistic Circuits: Inference, Representations, Learning and Theory

UCLA Computer Science Department - CS201 Seminar