Korshunova, I;
Gal, Y;
Gretton, A;
Dambre, J;
(2020)
Conditional BRUNO: A neural process for exchangeable labelled data.
Neurocomputing
, 416
pp. 305-309.
10.1016/j.neucom.2019.11.108.
Preview |
Text
BRUNO_main.pdf - Accepted Version Download (698kB) | Preview |
Abstract
We present a neural process which models exchangeable sequences of high-dimensional complex observations conditionally on a set of labels or tags. Our model combines the expressiveness of deep neural networks with the data-efficiency of Gaussian processes, resulting in a probabilistic model for which the posterior distribution is easy to evaluate and sample from, and the computational complexity scales linearly with the number of observations. The advantages of the proposed architecture are demonstrated on a challenging few-shot view reconstruction task which requires generalization from short sequences of viewpoints, and a contextual bandits problem.
| Type: | Article |
|---|---|
| Title: | Conditional BRUNO: A neural process for exchangeable labelled data |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1016/j.neucom.2019.11.108 |
| Publisher version: | https://doi.org/10.1016/j.neucom.2019.11.108 |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| Keywords: | exchangeability, meta-learning, conditional density estimation |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Life Sciences UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Life Sciences > Gatsby Computational Neurosci Unit |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10096552 |
Archive Staff Only
 |
View Item |
