Estimating Model Uncertainty of Neural Network in Sparse Information Form

Part of Proceedings of the International Conference on Machine Learning 1 pre-proceedings (ICML 2020)

Bibtex »Metadata »Paper »Supplemental »

Bibtek download is not availble in the pre-proceeding


Jongseok Lee, Matthias Humt, Jianxiang Feng, Rudolph Triebel


<p>We present a sparse representation of model uncertainty for Deep Neural Networks (DNNs) where the parameter posterior is approximated with an inverse formulation of the Multivariate Normal Distribution (MND), also known as the information form. The key insight of our work is that the information matrix, i.e. the inverse of the covariance matrix tends to be sparse in its spectrum. Therefore, dimensionality reduction techniques such as low rank approximations can be effectively exploited. To achieve this, we develop a novel sparsification algorithm and derive a cost-effective analytical sampler. As a result, we show that the information form of MND can be scalably applied to represent model uncertainty in MND. Our exhaustive theoretical analysis and empirical evaluations on various benchmarks show the competitiveness of our approach over the current methods.</p>