Abstract
In many statistical problems, a more coarse-grained model may be suitable for population-level behaviour, whereas a more detailed model is appropriate for accurate modelling of individual behaviour. This raises the question of how to integrate both types of models. Methods such as posterior regularization follow the idea of generalized moment matching, in that they allow matching expectations between two models, but sometimes both models are most conveniently expressed as latent variable models. We propose latent Bayesian melding, which is motivated by averaging the distributions over populations statistics of both the individual-level and the population-level models under a logarithmic opinion pool framework. In a case study on electricity disaggregation, which is a type of singlechannel blind source separation problem, we show that latent Bayesian melding leads to significantly more accurate predictions than an approach based solely on generalized moment matching.
Original language | English |
---|---|
Pages (from-to) | 3618-3626 |
Number of pages | 9 |
Journal | Advances in Neural Information Processing Systems |
Volume | 2 |
DOIs | |
Publication status | Published - 1 Dec 2015 |
Event | 29th Annual Conference on Neural Information Processing Systems, NIPS 2015 - Montreal, Canada Duration: 7 Dec 2015 → 12 Dec 2015 |
Bibliographical note
This work is supported by the Engineering and Physical Sciences Research Council, UK (grant numbers EP/K002732/1 and EP/M008223/1).Fingerprint
Dive into the research topics of 'Latent Bayesian melding for integrating individual and population models'. Together they form a unique fingerprint.Profiles
-
Mingjun Zhong
- School of Natural & Computing Sciences, Computing Science - Lecturer
- Machine Learning
- Centre for Energy Transition
Person: Academic