UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Doubly Stochastic Variational Inference for Deep Gaussian Processes

Salimbeni, H; Deisenroth, MP; (2017) Doubly Stochastic Variational Inference for Deep Gaussian Processes. In: Guyon, I and Luxburg, UV and Bengio, S and Wallach, HM and Fergus, R and Vishwanathan, SVN and Garnett, R, (eds.) Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS 2017). (pp. pp. 4591-4602). Neural Information Processing Systems (NIPS): Long Beach, CA, USA. Green open access

[thumbnail of 7045-doubly-stochastic-variational-inference-for-deep-gaussian-processes.pdf]
Preview
Text
7045-doubly-stochastic-variational-inference-for-deep-gaussian-processes.pdf - Published Version

Download (415kB) | Preview

Abstract

Deep Gaussian processes (DGPs) are multi-layer generalizations of GPs, but inference in these models has proved challenging. Existing approaches to inference in DGP models assume approximate posteriors that force independence between the layers, and do not work well in practice. We present a doubly stochastic variational inference algorithm, which does not force independence between layers. With our method of inference we demonstrate that a DGP model can be used effectively on data ranging in size from hundreds to a billion points. We provide strong empirical evidence that our inference scheme for DGPs works well in practice in both classification and regression.

Type: Proceedings paper
Title: Doubly Stochastic Variational Inference for Deep Gaussian Processes
Event: 31st Conference on Neural Information Processing Systems (NIPS 2017), 4-9 December 2017, Long Beach, CA, USA
Open access status: An open access version is available from UCL Discovery
Publisher version: http://papers.nips.cc/paper/7045-doubly-stochastic...
Language: English
Additional information: This version is the version of record. For information on re-use, please refer to the publisher’s terms and conditions.
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI: https://discovery.ucl.ac.uk/id/eprint/10083555
Downloads since deposit
61Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item