Matthew Willetts

Matthew Willetts

deep generative models, VAEs, deep learning, variational inference, Bayesian methods

I am a Research Fellow at UCL Computer Science and a Visiting Researcher at the Alan Turing Institute in London. Previously I obtained my DPhil in Computational Statistics and Machine Learning at the University of Oxford.

My work is on combining deep learning with Bayesian statistics. The resulting class of models, deep generative models enable us to scale Bayesian approaches to large datasets and complex data like images.

Publications

2022

  • F. Falck , C. Williams , D. Danks , G. Deligiannidis , C. Yau , C. Holmes , A. Doucet , M. Willetts , A Multi-Resolution Framework for U-Nets with Applications to Hierarchical VAEs, Advances in Neural Information Processing Systems, 2022.

2021

  • F. Falck , H. Zhang , M. Willetts , G. Nicholson , C. Yau , C. Holmes , Multi-Facet Clustering Variational Autoencoders, Advances in Neural Information Processing Systems, 2021.
  • M. Willetts , A. Camuto , T. Rainforth , S. Roberts , C. Holmes , Improving VAEs’ Robustness to Adversarial Attack, in International Conference on Learning Representations (ICLR), 2021.
  • A. Camuto , M. Willetts , B. Paige , C. Holmes , S. Roberts , Learning Bijective Feature Maps for Linear ICA, in International Conference on Artificial Intelligence and Statistics (AISTATS), 2021.
  • A. Camuto , M. Willetts , S. Roberts , C. Holmes , T. Rainforth , Towards a Theoretical Understanding of the Robustness of Variational Autoencoders, in International Conference on Artificial Intelligence and Statistics (AISTATS), 2021.
  • A. Camuto , M. Willetts , Variational Autoencoders: A Harmonic Perspective, in arXiv preprint, 2021.
  • B. Barrett , A. Camuto , M. Willetts , T. Rainforth , Certifiably Robust Variational Autoencoders , in arXiv preprint, 2021.
  • M. Willetts , B. Paige , I Don’t Need u: Identifiable Non-Linear ICA Without Side Information, in arXiv preprint, 2021.

2020

  • M. Willetts , X. Miscouridou , S. Roberts , C. Holmes , Relaxed-Responsibility Hierarchical Discrete VAEs, arXiv preprint, 2020.
  • A. Camuto , M. Willetts , U. Şimşekli , S. Roberts , C. Holmes , Explicit Regularisation in Gaussian Noise Injections, in Advances in Neural Information Processing Systems (NeurIPS), 2020.
  • M. Willetts , S. Roberts , C. Holmes , Semi-Unsupervised Learning: Clustering and Classifying using Ultra-Sparse Labels, in IEEE Conference on Big Data – Special Session on Machine Learning for Big Data, 2020.

2019

  • M. Willetts , S. Roberts , C. Holmes , Disentangling to Cluster: Gaussian Mixture Variational Ladder Autoencoders, in NeurIPS Bayesian Deep Learning Workshop, 2019.

2018

  • M. Willetts , S. Hollowell , L. Aslett , C. Holmes , A. Doherty , Statistical machine learning of sleep and physical activity phenotypes from sensor data in 96, 220 UK Biobank participants, Scientific Reports, 2018.
  • M. Willetts , S. Roberts , C. Holmes , Semi-Unsupervised Learning using Deep Generative Models, in NeurIPS Bayesian Deep Learning Workshop, 2018.
  • M. Willetts , A. Doherty , S. Roberts , C. Holmes , Semi-Unsupervised Learning of Human Activity using Deep Generative Models, in NeurIPS ML4Health Workshop, 2018.