3 papers
stat.ML2024
Structured Partial Stochasticity in Bayesian Neural Networks
Tommy Rochussen
Bayesian neural network posterior distributions have a great number of modes that correspond to the same network function. The abundance of such modes can make it difficult for app…
stat.ML2023
Amortised Inference in Neural Networks for Small-Scale Probabilistic Meta-Learning
Matthew Ashman, Tommy Rochussen, Adrian Weller
The global inducing point variational approximation for BNNs is based on using a set of inducing inputs to construct a series of conditional distributions that accurately approxima…
stat.ML2023
Amortised Inference in Bayesian Neural Networks
Tommy Rochussen
Meta-learning is a framework in which machine learning models train over a set of datasets in order to produce predictions on new datasets at test time. Probabilistic meta-learning…