v161: Proceedings of UAI 2021

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

Summary

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 and managing uncertainty in AI systems. Papers explore diverse methodologies including scalable variational inference for state space models, meta-learning improvements like Task Similarity Aware MAML, and efficient debiased evidence estimation using multilevel Monte Carlo sampling. Key contributions span advancements in Bayesian deep neural networks, causal inference with unobserved variables, robust reinforcement learning, and novel approaches to anomaly detection and adversarial defense. The volume also addresses critical aspects such as uncertainty calibration, interpretability, fairness in classification, and privacy in distributed learning, showcasing a comprehensive effort to enhance the reliability and understanding of AI.

Key takeaway

The 37th Conference on Uncertainty in Artificial Intelligence (UAI 2021) proceedings offer over 200 papers tackling the fundamental problem of uncertainty in AI systems. Key contributions span advancements in scalable Bayesian inference, robust reinforcement learning, causal discovery with unobserved variables, and improved uncertainty calibration for deep neural networks. This collection provides essential insights for researchers and practitioners aiming to build more reliable, interpretable, and trustworthy AI applications across diverse domains.

Topics

• Uncertainty Quantification
• Bayesian Inference
• Reinforcement Learning
• Causal Inference
• Deep Learning Architectures

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

Related on AIssential

• v216: Proceedings of UAI 2023 — 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.
• v180: Proceedings of UAI 2022 — This volume compiles the proceedings of the Thirty-Eighth Conference on Uncertainty in Artificial Intelligence (UAI 2022), held from August 1-5, 2022, in Eindhoven, The Netherlands, featuring research…
• 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.
• Structure-Aware Epistemic Uncertainty Quantification for Neural Operator PDE Surrogates — Restricting uncertainty sampling to the lifting module improves neural operator uncertainty quantification efficiency and accuracy.
• 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.