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

[164], , and . An Introduction to Lifted Probabilistic Inference, MIT Press, .
[163], , , , and . Towards an Interpretable Latent Space in Structured Models for Video Prediction, In IJCAI 2021 Weakly Supervised Representation Learning Workshop (WSRL), .
[162], and . Probabilistic Sufficient Explanations, In Proceedings of the 30th International Joint Conference on Artificial Intelligence (IJCAI), .
[161], , , , and . Model Checking Finite-Horizon Markov Chains with Probabilistic Inference, In Proceedings of the 33rd International Conference on Computer-Aided Verification (CAV), .
[160], and . Probabilistic Generating Circuits, In Proceedings of the UAI Workshop on Tractable Probabilistic Modeling (TPM), . TPM best paper award
[159] and . Tractable Regularization of Probabilistic Circuits, In Proceedings of the UAI Workshop on Tractable Probabilistic Modeling (TPM), .
[158], , , and . Is Parameter Learning via Weighted Model Integration Tractable?, In Proceedings of the UAI Workshop on Tractable Probabilistic Modeling (TPM), .
[157], , , and . A Compositional Atlas of Tractable Circuit Operations for Probabilistic Inference, In Proceedings of the UAI Workshop on Tractable Probabilistic Modeling (TPM), .
[156], , and . Tractable Computation of Expected Kernels, In Proceedings of the 37th Conference on Uncertainty in Aritifical Intelligence (UAI), .
[155], and . Probabilistic Generating Circuits, In Proceedings of the 38th International Conference on Machine Learning (ICML), . Long presentation, acceptance rate 166/5513 = 3%

Recent Talks

Invited Talk — Apr 2021  
Invited Talk — Apr 2021