Matthew Willetts

According to our database, Matthew Willetts authored at least 17 papers between 2018 and 2022.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2022

A Multi-Resolution Framework for U-Nets with Applications to Hierarchical VAEs.

Fabian Falck, Christopher Williams, Dominic Danks, George Deligiannidis, Christopher Yau, Chris C. Holmes, Arnaud Doucet, Matthew Willetts

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Variational Autoencoders: A Harmonic Perspective.

Alexander Camuto, Matthew Willetts

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022

Certifiably Robust Variational Autoencoders.

Ben Barrett, Alexander Camuto, Matthew Willetts, Tom Rainforth

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022

2021

I Don't Need u: Identifiable Non-Linear ICA Without Side Information.

Matthew Willetts, Brooks Paige

CoRR, 2021

Multi-Facet Clustering Variational Autoencoders.

Fabian Falck, Haoting Zhang, Matthew Willetts, George Nicholson, Christopher Yau, Chris C. Holmes

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Improving VAEs' Robustness to Adversarial Attack.

Matthew Willetts, Alexander Camuto, Tom Rainforth, Stephen J. Roberts, Christopher C. Holmes

Proceedings of the 9th International Conference on Learning Representations, 2021

Towards a Theoretical Understanding of the Robustness of Variational Autoencoders.

Alexander Camuto, Matthew Willetts, Stephen J. Roberts, Chris C. Holmes, Tom Rainforth

Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

Learning Bijective Feature Maps for Linear ICA.

Alexander Camuto, Matthew Willetts, Chris C. Holmes, Brooks Paige, Stephen J. Roberts

Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

2020

Relaxed-Responsibility Hierarchical Discrete VAEs.

Matthew Willetts, Xenia Miscouridou, Stephen J. Roberts, Chris C. Holmes

CoRR, 2020

Non-Determinism in TensorFlow ResNets.

Miguel Morin, Matthew Willetts

CoRR, 2020

Explicit Regularisation in Gaussian Noise Injections.

Alexander Camuto, Matthew Willetts, Umut Simsekli, Stephen J. Roberts, Chris C. Holmes

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Semi-Unsupervised Learning: Clustering and Classifying using Ultra-Sparse Labels.

Matthew Willetts, Stephen J. Roberts, Chris C. Holmes

Proceedings of the 2020 IEEE International Conference on Big Data (IEEE BigData 2020), 2020

2019

Regularising Deep Networks with DGMs.

Matthew Willetts, Alexander Camuto, Stephen J. Roberts, Chris C. Holmes

CoRR, 2019

Disentangling to Cluster: Gaussian Mixture Variational Ladder Autoencoders.

Matthew Willetts, Stephen J. Roberts, Chris C. Holmes

CoRR, 2019

Disentangling Improves VAEs' Robustness to Adversarial Attacks.

Matthew Willetts, Alexander Camuto, Stephen J. Roberts, Chris C. Holmes

CoRR, 2019

Semi-Unsupervised Learning with Deep Generative Models: Clustering and Classifying using Ultra-Sparse Labels.

Matthew Willetts, Stephen J. Roberts, Christopher C. Holmes

CoRR, 2019

2018

Semi-unsupervised Learning of Human Activity using Deep Generative Models.

Matthew Willetts, Aiden R. Doherty, Stephen J. Roberts, Chris C. Holmes

CoRR, 2018