PuSH - Publication Server of Helmholtz Zentrum München

Rochussen, T. ; Fortuin, V.

Sparse Gaussian Neural Processes.

In: (2025 Symposium on Advances in Approximate Bayesian Inference-AABI, 29 April 2025, Singapor). 1269 Law St, San Diego, Ca, United States: Jmlr-journal Machine Learning Research, 2025. 26 ( ; 289)
Publ. Version/Full Text
Open Access Hybrid
Despite significant recent advances in probabilistic meta-learning, it is common for practitioners to avoid using deep learning models due to a comparative lack of interpretability. Instead, many practitioners simply use non-meta-models such as Gaussian processes with interpretable priors, and conduct the tedious procedure of training their model from scratch for each task they encounter. While this is justifiable for tasks with a limited number of data points, the cubic computational cost of exact Gaussian process inference renders this prohibitive when each task has many observations. To remedy this, we introduce a family of models that meta-learn sparse Gaussian process inference. Not only does this enable rapid prediction on new tasks with sparse Gaussian processes, but since our models have clear interpretations as members of the neural process family, it also allows manual elicitation of priors in a neural process for the first time. In meta-learning regimes for which the number of observed tasks is small or for which expert domain knowledge is available, this offers a crucial advantage.
Additional Metrics?
[➜Log in]
Edit extra informations Login
Publication type Article: Conference contribution
ISSN (print) / ISBN 2640-3498
Conference Title 2025 Symposium on Advances in Approximate Bayesian Inference-AABI
Conference Date 29 April 2025
Conference Location Singapor
Quellenangaben Volume: 289, Issue: , Pages: 26 Article Number: , Supplement: ,
Publisher Jmlr-journal Machine Learning Research
Publishing Place 1269 Law St, San Diego, Ca, United States
Institute(s) Helmholtz Artifical Intelligence Cooperation Unit (HAICU)
Grants Branco Weiss Fellowship