Hirt, M; Dellaportas, P; Durmus, A; (2019) Copula-like variational inference. In: Proceedings of the 33rd Conference on Neural Information Processing Systems (NeurIPS 2019). 33rd Conference on Neural Information Processing Systems (NeurIPS 2019): Vancouver, Canada.

Preview

Text Dellaportas_Copula-like variational inference_VoR.pdf - Published Version Download (482kB) | Preview

Abstract

This paper considers a new family of variational distributions motivated by Sklar's theorem. This family is based on new copula-like densities on the hypercube with non-uniform marginals which can be sampled efficiently, i.e. with a complexity linear in the dimension d of the state space. Then, the proposed variational densities that we suggest can be seen as arising from these copula-like densities used as base distributions on the hypercube with Gaussian quantile functions and sparse rotation matrices as normalizing flows. The latter correspond to a rotation of the marginals with complexity O(d log d). We provide some empirical evidence that such a variational family can also approximate non-Gaussian posteriors and can be beneficial compared to Gaussian approximations. Our method performs largely comparably to state-of-the-art variational approximations on standard regression and classification benchmarks for Bayesian Neural Networks.

Download activity - last month

Export as CSVXMLJSON

Download activity - last 12 months

Export as XMLCSVJSON

Downloads by country - last 12 months

Export as CSVXMLJSON

Archive Staff Only

View Item