My research interests are motivated by the need for the effective and efficient deployment of probabilistic machine learning techniques to improve decision making and prediction in the presence of uncertainty.


  1. Andrei Margeloiu*, Matthew Ashman*, Umang Bhatt*, Yanzhi Chen, Mateja Jamnik, Adrian Weller
    Do Concept Bottleneck Models Learn As Intended?
    ICLR Workshop on Responsible AI, 2021.

  2. Metod Jazbec, Matthew Ashman, Vincent Fortuin, Micheal Pearce, Stephen Mandt, Gunnar Rätsch
    Scalable Gaussian Process Variational Autoencoders
    International Conference on Artificial Intelligence and Statistics (AISTATS), 2021.

  3. Matthew Ashman, Jonathan So, Will Tebbutt, Vincent Fortuin, Michael Pearce, Richard E. Turner
    Sparse Gaussian Process Variational Autoencoders
    arxiv, 2021