paper-with-me

Papers

Meta-Learning Reliable Priors in the Function Space

2021-06-06 · NeurIPS 2021 12 · Jonas Rothfuss, Dominique Heyn, Jinfan Chen, Andreas Krause

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.

📄 PDF Abstract BibTeX arXiv:2106.03195

Code (0)

등록된 구현이 없습니다.

Tasks

Bayesian OptimizationDecision MakingMeta-LearningSequential Decision MakingUncertainty Quantification

Similar Papers 제목 키워드 기반

Meta-Learning Priors for Safe Bayesian Optimization

2022-10-03 · Jonas Rothfuss, Christopher Koenig, Alisa Rupenyan, Andreas Krause

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 Quantification

MARS: Meta-Learning as Score Matching in the Function Space

2022-10-24 · Krunoslav Lehman Pavasovic, Jonas Rothfuss, Andreas Krause

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-Learning

Function-Space Empirical Bayes Regularisation with Large Vision-Language Model Priors

2026-02-03 · Pengcheng Hao, Huaze Tang, Ercan Engin Kuruoglu, Wenbo Ding arxiv

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 Inference

Meta-Learning 3D Shape Segmentation Functions

2021-10-08 · Yu Hao, Hao Huang, Shuaihang Yuan, Yi Fang

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-LearningSegmentation

Function-Space Empirical Bayes Regularisation with Student's t Priors

2026-02-25 · Pengcheng Hao, Ercan Engin Kuruoglu arxiv

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