1k citations · 5.3k across the 132 of their papers we have counts for
9 papers · 1 filter
Vector-valued Gaussian Processes on Riemannian Manifolds via Gauge Independent Projected Kernels
Michael Hutchinson, Alexander Terenin, Viacheslav Borovitskiy +3
Gaussian processes are machine learning models capable of learning unknown functions in a way that represents uncertainty, thereby facilitating construction of optimal decision-mak…
Powerpropagation: A sparsity inducing weight reparameterisation
Jonathan Schwarz, Siddhant M. Jayakumar, Razvan Pascanu +2
The training of sparse neural networks is becoming an increasingly important tool for reducing the computational footprint of models at training and evaluation, as well enabling th…
Interoperability of statistical models in pandemic preparedness: principles and reality
George Nicholson, Marta Blangiardo, Mark Briers +12
We present "interoperability" as a guiding framework for statistical modelling to assist policy makers asking multiple questions using diverse datasets in the face of an evolving p…
Group Equivariant Subsampling
Jin Xu, Hyunjik Kim, Tom Rainforth +1
Subsampling is used in convolutional neural networks (CNNs) in the form of pooling or strided convolutions, to reduce the spatial dimensions of feature maps and to allow the recept…
BayesIMP: Uncertainty Quantification for Causal Data Fusion
Siu Lun Chau, Jean-François Ton, Javier González +2
While causal models are becoming one of the mainstays of machine learning, the problem of uncertainty quantification in causal inference remains challenging. In this paper, we stud…
On Incorporating Inductive Biases into VAEs
Ning Miao, Emile Mathieu, N. Siddharth +2
We explain why directly changing the prior can be a surprisingly ineffective mechanism for incorporating inductive biases into VAEs, and introduce a simple and effective alternativ…