I am a Senior Lecturer in Machine Learning at the School of Informatics of the University of Edinburgh, affiliated with the Institute for Adaptive & Neural Computation.
My research is in machine learning for science, with a focus on developing methods for (Bayesian) inference and design.
Recent papers:
- New on arXiv: Improving Variational Autoencoder Estimation from Incomplete Data with Mixture Variational Families
- eLife: Designing Optimal Behavioral Experiments Using Machine Learning
- TMLR: Conditional Sampling of Variational Autoencoders via Iterated Approximate Ancestral Sampling
-
JMLR: Variational Gibbs Inference for Statistical Model Estimation from Incomplete Data
- ICML: Is Learning Summary Statistics Necessary for Likelihood-free Inference?
- TMLR: Estimating the Density Ratio between Distributions with High Discrepancy using Multinomial Logistic Regression
- TMLR: Bayesian Optimization with Informative Covariance