Meta-Learning Reliable Priors in the Function Space
When data are scarce meta-learning can improve a learner's accuracy by harnessing previous experience from related learning tasks. However, existing methods have unreliable uncertainty estimates which are often overconfident. Addressing these shortcomings, we introduce a novel meta-learning framework, called F-PACOH, that treats meta-learned priors as stochastic processes and performs meta-level regularization directly in the function space. This allows us to directly steer the probabilistic predictions of the meta-learner towards high epistemic uncertainty in regions of insufficient meta-training data and, thus, obtain well-calibrated uncertainty estimates. Finally, we showcase how our approach can be integrated with sequential decision making, where reliable uncertainty quantification is imperative. In our benchmark study on meta-learning for Bayesian Optimization (BO), F-PACOH significantly outperforms all other meta-learners and standard baselines.
Code (0)
등록된 구현이 없습니다.
Tasks
Bayesian OptimizationDecision MakingMeta-LearningSequential Decision MakingUncertainty QuantificationSimilar Papers 제목 키워드 기반
Meta-Learning Priors for Safe Bayesian Optimization
In robotics, optimizing controller parameters under safety constraints is an important challenge. Safe Bayesian optimization (BO) quantifies uncertainty in the objective and constraints to safely guide exploration in suc…
Bayesian OptimizationMeta-LearningUncertainty QuantificationMARS: Meta-Learning as Score Matching in the Function Space
Meta-learning aims to extract useful inductive biases from a set of related datasets. In Bayesian meta-learning, this is typically achieved by constructing a prior distribution over neural network parameters. However, sp…
Meta-LearningFunction-Space Empirical Bayes Regularisation with Large Vision-Language Model Priors
Bayesian deep learning (BDL) provides a principled framework for reliable uncertainty quantification by combining deep neural networks with Bayesian inference. A central challenge in BDL lies in the design of informative…
Bayesian InferenceMeta-Learning 3D Shape Segmentation Functions
Learning robust 3D shape segmentation functions with deep neural networks has emerged as a powerful paradigm, offering promising performance in producing a consistent part segmentation of each 3D shape. Generalizing acro…
3D Shape ReconstructionMeta-LearningSegmentationFunction-Space Empirical Bayes Regularisation with Student's t Priors
Bayesian deep learning (BDL) has emerged as a principled approach to produce reliable uncertainty estimates by integrating deep neural networks with Bayesian inference, and the selection of informative prior distribution…
Bayesian Inference