Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Meta-Learning Reliable Priors in the Function Space
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| regularize the meta-learned prior directly in function space rather than over prior parameters | F-PACOH · Calibration and uncertainty quantification | calibration | Helped |
| use F-PACOH instead of the compared meta-learners and standard baselines | Bayesian Optimization · Simulated benchmarks and hyper-parameter tuning | simple regret | Helped |
| use function-space meta-regularization in lifelong BO | F-PACOH · Lifelong Bayesian Optimization | BO performance | Helped |
| use F-PACOH rather than the other meta-learners | Lifelong Bayesian Optimization · Lifelong BO task sequence | simple regret | Helped |
Closest papers by meaning
- PACOH: Bayes-Optimal Meta-Learning with PAC-Guarantees (ICML 2021 · similarity 0.93)
- MARS: Meta-learning as Score Matching in the Function Space (ICLR 2023 · similarity 0.92)
- More Flexible PAC-Bayesian Meta-Learning by Learning Learning Algorithms (ICML 2024 · similarity 0.90)
- Meta-Learning by Adjusting Priors Based on Extended PAC-Bayes Theory (ICML 2018 · similarity 0.89)
- MALIBO: Meta-learning for Likelihood-free Bayesian Optimization (ICML 2024 · similarity 0.89)
- Amortized Bayesian Meta-Learning (ICLR 2019 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.