Efficient variational Bayesian neural network ensembles for outlier detection
arXiv:1703.06749v214 citations
Originality Synthesis-oriented
AI Analysis
This work addresses outlier detection for data analysis applications, but it is incremental as it builds on existing variational and ensembling techniques.
The authors tackled outlier detection by using ensembles of neural networks derived from variational Bayesian approximations, achieving results comparable to other efficient ensembling methods.
In this work we perform outlier detection using ensembles of neural networks obtained by variational approximation of the posterior in a Bayesian neural network setting. The variational parameters are obtained by sampling from the true posterior by gradient descent. We show our outlier detection results are comparable to those obtained using other efficient ensembling methods.