4 citations · 8 across the 6 of their papers we have counts for
7 papers
Function-space Parameterization of Neural Networks for Sequential Learning
Aidan Scannell, Riccardo Mereu, Paul Chang +3
Sequential learning paradigms pose challenges for gradient-based deep learning due to difficulties incorporating new data and retaining prior knowledge. While Gaussian processes el…
Sparse Function-space Representation of Neural Networks
Aidan Scannell, Riccardo Mereu, Paul Chang +3
Deep neural networks (NNs) are known to lack uncertainty estimates and struggle to incorporate new data. We present a method that mitigates these issues by converting NNs from weig…
Memory-Based Dual Gaussian Processes for Sequential Learning
Paul E. Chang, Prakhar Verma, S. T. John +2
Sequential learning with Gaussian processes (GPs) is challenging when access to past data is limited, for example, in continual and active learning. In such cases, errors can accum…
Fantasizing with Dual GPs in Bayesian Optimization and Active Learning
Paul E. Chang, Prakhar Verma, ST John +3
Gaussian processes (GPs) are the main surrogate functions used for sequential modelling such as Bayesian Optimization and Active Learning. Their drawbacks are poor scaling with dat…
Dual Parameterization of Sparse Variational Gaussian Processes
Vincent Adam, Paul E. Chang, Mohammad Emtiyaz Khan +1
Sparse variational Gaussian process (SVGP) methods are a common choice for non-conjugate Gaussian process inference because of their computational benefits. In this paper, we impro…
Fast Variational Learning in State-Space Gaussian Process Models
Paul E. Chang, William J. Wilkinson, Mohammad Emtiyaz Khan +1
Gaussian process (GP) regression with 1D inputs can often be performed in linear time via a stochastic differential equation formulation. However, for non-Gaussian likelihoods, thi…