2023

Towards Anytime Classification in Early-Exit Architectures by Enforcing Conditional Monotonicity

M. Jazbec, J. U. Allingham, D. Zhang, E. Nalisnick.
37th Conference on Neural Information Processing Systems (NeurIPS). 2023.
Paper

A Simple Zero-shot Prompt Weighting Technique to Improve Prompt Ensembling in Text-image Models

J. U. Allingham, J. Ren, M. W. Dusenberry, X. Gu, Y. Cui, D. Tran, J. Z. Liu, B. Lakshminarayanan.
40th International Conference on Machine Learning (ICML). 2023.
Paper, Poster, Code

2022

Learning Generative Models with Invariance to Symmetries

J. U. Allingham, J. Antorán, S. Padhy, E. Nalisnick, J. M, Hernández-Lobato.
NeurIPS 2022 Workshop on Symmetry and Geometry in Neural Representations.
Paper, Poster

Sparse MoEs meet Efficient Ensembles

J. U. Allingham, F. Wenzel, Z. E. Mariet, B. Mustafa, J. Puigcerver, N. Houlsby, G. Jerfel, V. Fortuin, B. Lakshminarayanan, J. Snoek, D. Tran, C. Riquelme Ruiz, R. Jenatton.
Transactions on Machine Learning Research, 2022.
Paper, Poster, Slides, Code

Adapting the Linearised Laplace Model Evidence for Modern Deep Learning

J. Antorán, J.U. Allingham, D. Janz, E. Daxberger, R. Barbano, E. Nalisnick, J. M. Hernández-Lobato.
39th International Conference on Machine Learning (ICML). 2022.
Paper

A Product of Experts Approach to Early-Exit Ensembles

J. U. Allingham, E. Nalisnick.
Workshop on Dynamic Neural Networks at ICML. 2022.
Paper, Poster

2021

Linearised Laplace Inference in Networks with Normalisation Layers and the Neural g-Prior

J. Antorán, J.U. Allingham, D. Janz, E. Daxberger, E. Nalisnick and J. M. Hernández-Lobato.
Contributed talk at 4th Symposium on Advances in Approximate Bayesian Inference (AABI). 2022.
Paper, Poster

Addressing Bias in Active Learning with Depth Uncertainty Networks… or Not

C Murray, J. U. Allingham, J. Antorán and J. M. Hernández-Lobato.
Contributed talk at I (Still) Can’t Believe It’s Not Better Workshop at NeurIPS. 2021.
Proceedings of Machine Learning Research, Volume 163. 2022.
Paper

Depth Uncertainty Networks for Active Learning

C Murray, J. U. Allingham, J. Antorán and J. M. Hernández-Lobato.
Bayesian Deep Learning Workshop at NeurIPS. 2021.
Paper

2020

Bayesian Deep Learning via Subnetwork Inference

E. Daxberger, J. U. Allingham*, E. Nalisnick*, J. Antorán* and J. M. Hernández-Lobato.
Contributed talk at 3rd Symposium on Advances in Approximate Bayesian Inference, 2020.
Paper, Poster

Depth Uncertainty in Neural Networks

J. U. Allingham*, J. Antorán* and J. M. Hernández-Lobato.
34th Conference on Neural Information Processing Systems (NeurIPS), Vancouver, Canada. 2020.
Paper, Poster, Code

Variational Depth Search in ResNets

J. U. Allingham*, J. Antorán* and J. M. Hernández-Lobato.
Contributed talk at 1st Workshop on Neural Architecture Search at ICLR 2020.
Paper, Poster, Code

2018

Unsupervised automatic dataset repair

J. Allingham.
MPhil Thesis (Awarded Distinction).
Thesis, Poster, Bibtex