v216: Proceedings of UAI 2023

2026-06-10 · Source: Proceedings of Machine Learning Research · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Robotics & Autonomous Systems, Cybersecurity & Data Privacy · Depth: Expert, extended

Summary

Volume 216 presents the proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence (UAI 2023), held in Pittsburgh, PA, USA, from August 31 to September 4, 2023. This collection features a broad spectrum of research dedicated to understanding, modeling, and mitigating uncertainty in AI systems. Contributions span critical areas such as reinforcement learning, causal inference, and federated learning, with a strong emphasis on robust and interpretable AI. Specific methodologies include Bayesian inference, Gaussian processes, graph neural networks, and novel approaches to calibration and out-of-distribution detection, highlighting the conference's focus on foundational and applied aspects of uncertainty in AI.

Key takeaway

The 39th Conference on Uncertainty in Artificial Intelligence (UAI 2023) presents significant advancements in quantifying and managing uncertainty across diverse AI domains. Key contributions span robust reinforcement learning, causal inference with missing data, privacy-preserving federated learning, and enhanced calibration techniques for deep neural networks. These insights are vital for AI researchers and practitioners aiming to develop more reliable, interpretable, and ethically sound AI systems.

Topics

• Uncertainty Quantification
• Reinforcement Learning
• Causal Inference
• Federated Learning
• Bayesian Methods

Code references

• JacobHA/Q-Bounding-in-Compositional-RL
• SakshiAgarwal/QAVI
• andrade-stats/TrimmedMarginalLikelihoodGP
• babau1/samba
• accountcreatedforuploadingUAIcode/UAI-2023

Best for: AI Scientist, Machine Learning Engineer, Research Scientist

Related on AIssential

• v161: Proceedings of UAI 2021 — The Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence (UAI 2021), held online from July 27-30, 2021, presents a broad collection of research focused on quantifying…
• v286: Proceedings of UAI 2025 — The conference proceedings showcase diverse research advancing AI's understanding and management of uncertainty, causality, and robust learning.
• Uncertainty-Aware Predictive Safety Filters for Probabilistic Neural Network Dynamics — UPSi enhances RL safety by integrating probabilistic neural networks with rigorous uncertainty quantification into predictive safety filters.
• Concerning Uncertainty -- A Systematic Survey of Uncertainty-Aware XAI — UAXAI integrates uncertainty into AI explanations to improve transparency, reliability, and human trust in high-stakes decision-making.
• Quantization Impact on the Accuracy and Communication Efficiency Trade-off in Federated Learning for Aerospace Predictive Maintenance — INT4 quantization offers FP32-equivalent accuracy with $8\times$ communication savings in federated learning for aerospace predictive maintenance.
• Inference, not prediction — Prof. Michael I. Jordan on what modern AI is still missing — Anthropomorphizing AI and AGI buzzwords distract from practical machine learning and economic system design.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Proceedings of Machine Learning Research.