Matthew Willetts

• Personal Webpage
• GitHub
• Twitter
• Google Scholar

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.
  

  @article{falck2022unet,
    title = {A Multi-Resolution Framework for U-Nets with Applications to Hierarchical VAEs},
    author = {Falck, Fabian and Williams, Christopher and Danks, Dominic and Deligiannidis, George and Yau, Christopher and Holmes, Chris and Doucet, Arnaud and Willetts, Matthew},
    journal = {Advances in Neural Information Processing Systems},
    year = {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.
  
  @article{falck2021mfcvae,
    title = {Multi-Facet Clustering Variational Autoencoders},
    author = {Falck, Fabian and Zhang, Haoting and Willetts, Matthew and Nicholson, George and Yau, Christopher and Holmes, Chris},
    journal = {Advances in Neural Information Processing Systems},
    year = {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.
  
  @inproceedings{Willetts2019VAEAdvRobustness,
    archiveprefix = {arXiv},
    arxivid = {1906.00230},
    author = {Willetts, Matthew and Camuto, Alexander and Rainforth, Tom and Roberts, Stephen and Holmes, Chris},
    eprint = {1906.00230},
    booktitle = {International Conference on Learning Representations (ICLR)},
    title = {{Improving VAEs' Robustness to Adversarial Attack}},
    year = {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.
  

  @inproceedings{Camuto2020BijectivaICA,
    archiveprefix = {arXiv},
    arxivid = {2002.07766v4},
    author = {Camuto, Alexander and Willetts, Matthew and Paige, Brooks and Holmes, Chris and Roberts, Stephen},
    eprint = {2002.07766v4},
    booktitle = {International Conference on Artificial Intelligence and Statistics (AISTATS)},
    title = {{Learning Bijective Feature Maps for Linear ICA}},
    year = {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.
  
  @inproceedings{Camuto2020VAERobustnessTheory,
    archiveprefix = {arXiv},
    arxivid = {2007.07365},
    author = {Camuto, Alexander and Willetts, Matthew and Roberts, Stephen and Holmes, Chris and Rainforth, Tom},
    eprint = {2007.07365},
    booktitle = {International Conference on Artificial Intelligence and Statistics (AISTATS)},
    title = {{Towards a Theoretical Understanding of the Robustness of Variational Autoencoders}},
    year = {2021}
  }
  

• A. Camuto , M. Willetts , Variational Autoencoders: A Harmonic Perspective, in arXiv preprint, 2021.
  

  @inproceedings{Camuto2021harmonic,
    archiveprefix = {arXiv},
    arxivid = {2105.14866},
    author = {Camuto, Alexander and Willetts, Matthew},
    eprint = {2105.14866},
    journal = {arXiv preprint},
    title = {{Variational Autoencoders: A Harmonic Perspective}},
    year = {2021}
  }
  

• B. Barrett , A. Camuto , M. Willetts , T. Rainforth , Certifiably Robust Variational Autoencoders , in arXiv preprint, 2021.
  

  @inproceedings{Barrett2021certifiable,
    archiveprefix = {arXiv},
    arxivid = {2102.07559},
    author = {Barrett, Ben and Camuto, Alexander and Willetts, Matthew and Rainforth, Tom},
    eprint = {2102.07559},
    journal = {arXiv preprint},
    title = {{Certifiably Robust Variational Autoencoders
    }},
    year = {2021}
  }
  

• M. Willetts , B. Paige , I Don’t Need u: Identifiable Non-Linear ICA Without Side Information, in arXiv preprint, 2021.
  

  @inproceedings{Willetts2021idontneedu,
    archiveprefix = {arXiv},
    arxivid = {2106.05238},
    author = {Willetts, Matthew and Paige, Brooks},
    eprint = {2106.05238},
    journal = {arXiv preprint},
    title = {{I Don't Need u: Identifiable Non-Linear ICA Without Side Information}},
    year = {2021}
  }
  

2020

• M. Willetts , X. Miscouridou , S. Roberts , C. Holmes , Relaxed-Responsibility Hierarchical Discrete VAEs, arXiv preprint, 2020.
  

  @article{Willetts2020HierarchicalDiscrete,
    archiveprefix = {arXiv},
    arxivid = {2007.07307v1},
    author = {Willetts, Matthew and Miscouridou, Xenia and Roberts, Stephen and Holmes, Chris},
    eprint = {2007.07307v1},
    journal = {arXiv preprint},
    title = {{Relaxed-Responsibility Hierarchical Discrete VAEs}},
    year = {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.
  
  @inproceedings{Camuto2020ExplicitReg,
    archiveprefix = {arXiv},
    arxivid = {2007.07368},
    author = {Camuto, Alexander and Willetts, Matthew and Şimşekli, Umut and Roberts, Stephen and Holmes, Chris},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    eprint = {2007.07368},
    title = {{Explicit Regularisation in Gaussian Noise Injections}},
    year = {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.
  

  @inproceedings{Willetts2020SemiUnsupervised,
    archiveprefix = {arXiv},
    arxivid = {1901.08560},
    author = {Willetts, Matthew and Roberts, Stephen and Holmes, Chris},
    booktitle = {IEEE Conference on Big Data – Special Session on Machine Learning for Big Data},
    eprint = {1901.08560},
    title = {{Semi-Unsupervised Learning: Clustering and Classifying using Ultra-Sparse Labels}},
    year = {2020}
  }
  

2019

• M. Willetts , S. Roberts , C. Holmes , Disentangling to Cluster: Gaussian Mixture Variational Ladder Autoencoders, in NeurIPS Bayesian Deep Learning Workshop, 2019.
  
  @inproceedings{Willetts2019DisentangledClustering,
    archiveprefix = {arXiv},
    arxivid = {1909.11501},
    author = {Willetts, Matthew and Roberts, Stephen and Holmes, Chris},
    booktitle = {NeurIPS Bayesian Deep Learning Workshop},
    eprint = {1909.11501},
    title = {{Disentangling to Cluster: Gaussian Mixture Variational Ladder Autoencoders}},
    year = {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.
  
  @article{Willetts2018ActivityHMM,
    author = {Willetts, Matthew and Hollowell, Sven and Aslett, Louis and Holmes, Chris and Doherty, Aiden},
    doi = {10.1038/s41598-018-26174-1},
    journal = {Scientific Reports},
    title = {{Statistical machine learning of sleep and physical activity phenotypes from sensor data in 96, 220 UK Biobank participants}},
    year = {2018}
  }
  

• M. Willetts , S. Roberts , C. Holmes , Semi-Unsupervised Learning using Deep Generative Models, in NeurIPS Bayesian Deep Learning Workshop, 2018.
  

  @inproceedings{Willetts2018SemiUnsupervised,
    author = {Willetts, Matthew and Roberts, Stephen and Holmes, Chris},
    booktitle = {NeurIPS Bayesian Deep Learning Workshop},
    title = {{Semi-Unsupervised Learning using Deep Generative Models}},
    year = {2018}
  }
  

• M. Willetts , A. Doherty , S. Roberts , C. Holmes , Semi-Unsupervised Learning of Human Activity using Deep Generative Models, in NeurIPS ML4Health Workshop, 2018.
  

  @inproceedings{Willetts2018ActivityDGM,
    archiveprefix = {arXiv},
    arxivid = {1810.12176v2},
    author = {Willetts, Matthew and Doherty, Aiden and Roberts, Stephen and Holmes, Chris},
    booktitle = {NeurIPS ML4Health Workshop},
    eprint = {1810.12176v2},
    title = {{Semi-Unsupervised Learning of Human Activity using Deep Generative Models}},
    year = {2018}
  }