Gaussian process conditional density estimation

File Description SizeFormat 
1810.12750.pdfAccepted version5.28 MBAdobe PDFView/Open
Title: Gaussian process conditional density estimation
Authors: Dutordoir, V
Salimbeni, HR
Hensman, J
Deisenroth, MP
Item Type: Conference Paper
Abstract: Conditional Density Estimation (CDE) models deal with estimating conditional distributions. The conditions imposed on the distribution are the inputs of the model. CDE is a challenging task as there is a fundamental trade-off between model complexity, representational capacity and overfitting. In this work, we propose to extend the model's input with latent variables and use Gaussian processes (GP) to map this augmented input onto samples from the conditional distribution. Our Bayesian approach allows for the modeling of small datasets, but we also provide the machinery for it to be applied to big data using stochastic variational inference. Our approach can be used to model densities even in sparse data regions, and allows for sharing learned structure between conditions. We illustrate the effectiveness and wide-reaching applicability of our model on a variety of real-world problems, such as spatio-temporal density estimation of taxi drop-offs, non-Gaussian noise modeling, and few-shot learning on omniglot images.
Issue Date: 3-Dec-2018
Date of Acceptance: 5-Sep-2018
Publisher: Neural Information Processing Systems Conference
Journal / Book Title: NIPS Proceedings
Volume: 31
Copyright Statement: © 2018 Neural Information Processing Systems Foundation, Inc.
Conference Name: Advances in Neural Information Processing Systems
Keywords: stat.ML
Publication Status: Published
Start Date: 2018-12-03
Finish Date: 2018-12-08
Conference Place: Montréal, Canada
Open Access location:
Appears in Collections:Computing

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Creative Commonsx