activity
20102020
most citedSlice sampling covariance hyperparameters of latent Gaussian models

117 citations · 456 across the 12 of their papers we have counts for

collaborators

12 papers

stat.ML20201 cited

Density Deconvolution with Normalizing Flows

Tim Dockhorn, James A. Ritchie, Yaoliang Yu +1

Density deconvolution is the task of estimating a probability density function given only noise-corrupted samples. We can fit a Gaussian mixture model to the underlying density by…

cs.LG202012 cited

Diverse Ensembles Improve Calibration

Asa Cooper Stickland, Iain Murray

Modern deep neural networks can produce badly calibrated predictions, especially when train and test distributions are mismatched. Training an ensemble of models and averaging thei…

stat.ML20201 cited

Ordering Dimensions with Nested Dropout Normalizing Flows

Artur Bekasov, Iain Murray

The latent space of normalizing flows must be of the same dimensionality as their output space. This constraint presents a problem if we want to learn low-dimensional, semantically…

stat.ML20192 cited

Scalable Extreme Deconvolution

James A. Ritchie, Iain Murray

The Extreme Deconvolution method fits a probability density to a dataset where each observation has Gaussian noise added with a known sample-specific covariance, originally intende…

cs.LG201933 cited

Dynamic Evaluation of Transformer Language Models

Ben Krause, Emmanuel Kahembwe, Iain Murray +1

This research note combines two methods that have recently improved the state of the art in language modeling: Transformers and dynamic evaluation. Transformers use stacked layers…

cs.LG2019113 cited

BERT and PALs: Projected Attention Layers for Efficient Adaptation in Multi-Task Learning

Asa Cooper Stickland, Iain Murray

Multi-task learning shares information between related tasks, sometimes reducing the number of parameters required. State-of-the-art results across multiple natural language unders…