Variational Bayesian optimal experimental design
Bayesian optimal experimental design (BOED) is a principled framework for making efficient use of limited experimental resources. Unfortunately, its applicability is hampered by the difficulty of obtaining accurate estimates of the expected information gain (EIG) of an experiment. To address this, w...
Автори: | Foster, A, Jankowiak, M, Bingham, E, Horsfall, P, Tee, YW, Rainforth, T, Goodman, N |
---|---|
Формат: | Conference item |
Опубліковано: |
Conference on Neural Information Processing Systems
2019
|
Схожі ресурси
Схожі ресурси
-
A unified stochastic gradient approach to designing Bayesian-optimal experiments
за авторством: Foster, A, та інші
Опубліковано: (2020) -
Modern Bayesian experimental design
за авторством: Rainforth, T, та інші
Опубліковано: (2024) -
Variational, Monte Carlo and policy-based approaches to Bayesian experimental design
за авторством: Foster, AE
Опубліковано: (2021) -
Making better use of unlabelled data in Bayesian Active learning
за авторством: Bickford Smith, F, та інші
Опубліковано: (2024) -
Bayesian Optimization for Probabilistic Programs
за авторством: Rainforth, T, та інші
Опубліковано: (2016)