This portal has been archived. Explore the next generation of this technology.
Functional Bayesian Neural Networks for Model Uncertainty Quantification
lib:91cc486e96cfc69b (v1.0.0)
Authors: Nanyang Ye,Zhanxing Zhu
Where published: ICLR 2019 5
Document: PDF DOI
Abstract URL: https://openreview.net/forum?id=SJxFN3RcFX
In this paper, we extend the Bayesian neural network to functional Bayesian neural network with functional Monte Carlo methods that use the samples of functionals instead of samples of networks' parameters for inference to overcome the curse of dimensionality for uncertainty quantification. Based on the previous work on Riemannian Langevin dynamics, we propose the stochastic gradient functional Riemannian dynamics for training functional Bayesian neural network. We show the effectiveness and efficiency of our proposed approach with various experiments.
Where published: ICLR 2019 5
Document: PDF DOI
Abstract URL: https://openreview.net/forum?id=SJxFN3RcFX
In this paper, we extend the Bayesian neural network to functional Bayesian neural network with functional Monte Carlo methods that use the samples of functionals instead of samples of networks' parameters for inference to overcome the curse of dimensionality for uncertainty quantification. Based on the previous work on Riemannian Langevin dynamics, we propose the stochastic gradient functional Riemannian dynamics for training functional Bayesian neural network. We show the effectiveness and efficiency of our proposed approach with various experiments.
Relevant initiatives
Related knowledge about this paper
Reproduced results (crowd-benchmarking and competitions)
Artifact and reproducibility checklists
- ACM/cTuning artifact appendix and reproducibility checklist
- NeurIPS reproducibility checklist
- SIGPLAN's checklist for empirical evaluation
- Collective Knowledge (organizing research projects based on FAIR principles)