5 papers
Investigating Batch Inference in a Sequential Monte Carlo Framework for Neural Networks
Andrew Millard, Joshua Murphy, Peter Green +1
Bayesian inference allows us to define a posterior distribution over the weights of a generic neural network (NN). Exact posteriors are usually intractable, in which case approxima…
Hess-MC2: Sequential Monte Carlo Squared using Hessian Information and Second Order Proposals
Joshua Murphy, Conor Rosato, Andrew Millard +3
When performing Bayesian inference using Sequential Monte Carlo (SMC) methods, two considerations arise: the accuracy of the posterior approximation and computational efficiency. T…
Humble your Overconfident Networks: Unlearning Overfitting via Sequential Monte Carlo Tempered Deep Ensembles
Andrew Millard, Zheng Zhao, Joshua Murphy +1
Sequential Monte Carlo (SMC) methods offer a principled approach to Bayesian uncertainty quantification but are traditionally limited by the need for full-batch gradient evaluation…
Utilising Gradient-Based Proposals Within Sequential Monte Carlo Samplers for Training of Partial Bayesian Neural Networks
Andrew Millard, Joshua Murphy, Simon Maskell +1
Partial Bayesian neural networks (pBNNs) have been shown to perform competitively with fully Bayesian neural networks while only having a subset of the parameters be stochastic. Us…
Incorporating the ChEES Criterion into Sequential Monte Carlo Samplers
Andrew Millard, Joshua Murphy, Daniel Frisch +1
Markov chain Monte Carlo (MCMC) methods are a powerful but computationally expensive way of performing non-parametric Bayesian inference. MCMC proposals which utilise gradients, su…