mlsanityData to 7 Oct 2026

Bayesian meta learning for trustworthy uncertainty quantification

arXiv 2407.19287 ↗First posted 27 Jul 2024stat.ML cs.LG cs.SYcited by 0

Not on the map. Why?

Abstract (arXiv)

We consider the problem of Bayesian regression with trustworthy uncertainty quantification. We define that the uncertainty quantification is trustworthy if the ground truth can be captured by intervals dependent on the predictive distributions with a pre-specified probability. Furthermore, we propose, Trust-Bayes, a novel optimization framework for Bayesian meta learning which is cognizant of trustworthy uncertainty quantification without explicit assumptions on the prior model/distribution of the functions. We characterize the lower bounds of the probabilities of the ground truth being captured by the specified intervals and analyze the sample complexity with respect to the feasible probability for trustworthy uncertainty quantification. Monte Carlo simulation of a case study using Gaussian process regression is conducted for verification and comparison with the Meta-prior algorithm.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 20 of its 40 references that are in the map. First posted on arXiv 27 Jul 2024.

Builds on

20 of 40 references.

References · 20

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  2. 2019Meta-Learning with Implicit Gradientscited by 523
  3. 2015Deep Kernel Learningcited by 440
  4. 2018Bayesian Model-Agnostic Meta-Learningcited by 194
  5. 2019Adaptive Gradient-Based Meta-Learning Methodscited by 183
  6. 2017A General Safety Framework for Learning-Based Control in Uncertain Robotic Systemscited by 150
  7. 2016Bayesian Optimization with Safety Constraints: Safe and Automatic Parameter Tuning in Roboticscited by 134
  8. 2020PACOH: Bayes-Optimal Meta-Learning with PAC-Guaranteescited by 85
  9. 2018Stagewise Safe Bayesian Optimization with Gaussian Processescited by 79
  10. 2021Shallow Bayesian Meta Learning for Real-World Few-Shot Recognitioncited by 48
  11. 2021Meta-Learning Sparse Implicit Neural Representationscited by 48
  12. 2018Meta-Learning Priors for Efficient Online Bayesian Regressioncited by 47
8 more
  1. 2021Generalization of Model-Agnostic Meta-Learning Algorithms: Recurring and Unseen Taskscited by 36
  2. 2017Safe Learning of Quadrotor Dynamics Using Barrier Certificatescited by 32
  3. 2017Random Feature-based Online Multi-kernel Learning in Environments with Unknown Dynamicscited by 28
  4. 2020Safe Active Dynamics Learning and Control: A Sequential Exploration-Exploitation Frameworkcited by 19
  5. 2020Control Barriers in Bayesian Learning of System Dynamicscited by 17
  6. 2020Bayesian Meta-Prior Learning Using Empirical Bayescited by 14
  7. 2021Lightweight Distributed Gaussian Process Regression for Online Machine Learningcited by 4
  8. 2022Distributed Safe Learning and Planning for Multi-robot Systemscited by 1

Built on by

Not cited yet.