
Diverse Ensembles Improve Calibration
Modern deep neural networks can produce badly calibrated predictions, es...
read it

Density Deconvolution with Normalizing Flows
Density deconvolution is the task of estimating a probability density fu...
read it

Ordering Dimensions with Nested Dropout Normalizing Flows
The latent space of normalizing flows must be of the same dimensionality...
read it

On Contrastive Learning for Likelihoodfree Inference
Likelihoodfree methods perform parameter inference in stochastic simula...
read it

Scalable Extreme Deconvolution
The Extreme Deconvolution method fits a probability density to a dataset...
read it

CloudLSTM: A Recurrent Neural Model for Spatiotemporal Pointcloud Stream Forecasting
This paper introduces CloudLSTM, a new branch of recurrent neural networ...
read it

Neural Spline Flows
A normalizing flow models a complex probability density as an invertible...
read it

CubicSpline Flows
A normalizing flow models a complex probability density as an invertible...
read it

Dynamic Evaluation of Transformer Language Models
This research note combines two methods that have recently improved the ...
read it

BERT and PALs: Projected Attention Layers for Efficient Adaptation in MultiTask Learning
Multitask learning allows the sharing of useful information between mul...
read it

Bayesian Adversarial Spheres: Bayesian Inference and Adversarial Examples in a Noiseless Setting
Modern deep neural network models suffer from adversarial examples, i.e....
read it

Sequential Neural Methods for Likelihoodfree Inference
Likelihoodfree inference refers to inference when a likelihood function...
read it

Mode Normalization
Normalization methods are a central building block in the deep learning ...
read it

Sequential Neural Likelihood: Fast Likelihoodfree Inference with Autoregressive Flows
We present Sequential Neural Likelihood (SNL), a new method for Bayesian...
read it

Model Criticism in Latent Space
Model criticism is usually carried out by assessing if replicated data g...
read it

Dynamic Evaluation of Neural Sequence Models
We present methodology for using dynamic evaluation to improve neural se...
read it

A determinantfree method to simulate the parameters of large Gaussian fields
We propose a determinantfree approach for simulationbased Bayesian inf...
read it

Masked Autoregressive Flow for Density Estimation
Autoregressive models are among the best performing neural density estim...
read it

Markov Chain Truncation for DoublyIntractable Inference
Computing partition functions, the normalizing constants of probability ...
read it

Multiplicative LSTM for sequence modelling
We introduce multiplicative LSTM (mLSTM), a recurrent neural network arc...
read it

Fast εfree Inference of Simulation Models with Bayesian Conditional Density Estimation
Many statistical models can be simulated forwards but have intractable l...
read it

Neural Autoregressive Distribution Estimation
We present Neural Autoregressive Distribution Estimation (NADE) models, ...
read it

Differentiation of the Cholesky decomposition
We review strategies for differentiating matrixbased computations, and ...
read it

MADE: Masked Autoencoder for Distribution Estimation
There has been a lot of recent interest in designing neural network mode...
read it

Incorporating Side Information in Probabilistic Matrix Factorization with Gaussian Processes
Probabilistic matrix factorization (PMF) is a powerful method for modeli...
read it

A Deep and Tractable Density Estimator
The Neural Autoregressive Distribution Estimator (NADE) and its realval...
read it

RNADE: The realvalued neural autoregressive densityestimator
We introduce RNADE, a new model for joint density estimation of realval...
read it

Parallel MCMC with Generalized Elliptical Slice Sampling
Probabilistic models are conceptually powerful tools for finding structu...
read it

Bayesian Learning in Undirected Graphical Models: Approximate MCMC algorithms
Bayesian learning in undirected graphical modelscomputing posterior dis...
read it

A Framework for Evaluating Approximation Methods for Gaussian Process Regression
Gaussian process (GP) predictors are an important component of many Baye...
read it

Elliptical slice sampling
Many probabilistic models introduce strong dependencies between variable...
read it
Iain Murray
is this you? claim profile
Reader in Machine Learning, School of Informatics at University of Edinburgh, ECAT (Edinburgh Clinical Academic Track) Clinical Lecturer and Specialty Registrar in Orthopaedic Surgery at the University of Edinburgh since 2010, Visiting Fellow at Santa Monica Orthopaedic and Sports Medicine Group from 20122013, Visiting Research Fellow at University of California, Los Angeles (UCLA) 20122013, Specialty Trainee in Trauma and Orthopaedic Surgery at NHS Lothian from 20092011, Foundation Doctor at NHS Lothian from 20072009