Michael U. Gutmann

I am a Senior Lecturer (Assoc Prof) 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

  • TMLR: Improving Variational Autoencoder Estimation from Incomplete Data with Mixture Variational Families [link]

  • eLife: Designing Optimal Behavioral Experiments Using Machine Learning [link]

  • TMLR: Conditional Sampling of Variational Autoencoders via Iterated Approximate Ancestral Sampling [link]

  • JMLR: Variational Gibbs Inference for Statistical Model Estimation from Incomplete Data [link]

  • ICML: Is Learning Summary Statistics Necessary for Likelihood-free Inference? [link]


CC BY-SA 4.0 Michael U. Gutmann. Last modified: September 24, 2024. Accessibility. Website built with Franklin.jl and the Julia programming language.