I
Iain Murray
Researcher at University of Edinburgh
Publications - 136
Citations - 9306
Iain Murray is an academic researcher from University of Edinburgh. The author has contributed to research in topics: Markov chain Monte Carlo & Autoregressive model. The author has an hindex of 40, co-authored 113 publications receiving 7739 citations. Previous affiliations of Iain Murray include Max Planck Society & University of Toronto.
Papers
More filters
Proceedings ArticleDOI
Evaluation methods for topic models
TL;DR: It is demonstrated experimentally that commonly-used methods are unlikely to accurately estimate the probability of held-out documents, and two alternative methods that are both accurate and efficient are proposed.
Proceedings Article
Masked Autoregressive Flow for Density Estimation
TL;DR: Masked autoregressive flow as mentioned in this paper is a generalization of Inverse Autoregressive Flow that uses the random numbers that the model uses internally when generating data for density estimation.
Proceedings Article
The Neural Autoregressive Distribution Estimator
Hugo Larochelle,Iain Murray +1 more
TL;DR: A new approach for modeling the distribution of high-dimensional vectors of discrete variables inspired by the restricted Boltzmann machine, which outperforms other multivariate binary distribution estimators on several datasets and performs similarly to a large (but intractable) RBM.
Proceedings ArticleDOI
On the quantitative analysis of deep belief networks
Ruslan Salakhutdinov,Iain Murray +1 more
TL;DR: It is shown that Annealed Importance Sampling (AIS) can be used to efficiently estimate the partition function of an RBM, and a novel AIS scheme for comparing RBM's with different architectures is presented.
Posted Content
MADE: Masked Autoencoder for Distribution Estimation
TL;DR: In this article, the autoencoder outputs are interpreted as a set of conditional probabilities, and their product, the full joint probability, and a single network can decompose the joint probability in multiple different orderings.