11 citations · 33 across the 10 of their papers we have counts for
7 papers · 1 filter
A Generative Model of Symmetry Transformations
James Urquhart Allingham, Bruno Kacper Mlodozeniec, Shreyas Padhy +5
Correctly capturing the symmetry transformations of data can lead to efficient models with strong generalization capabilities, though methods incorporating symmetries often require…
Towards Anytime Classification in Early-Exit Architectures by Enforcing Conditional Monotonicity
Metod Jazbec, James Urquhart Allingham, Dan Zhang +1
Modern predictive models are often deployed to environments in which computational budgets are dynamic. Anytime algorithms are well-suited to such environments as, at any point dur…
A Simple Zero-shot Prompt Weighting Technique to Improve Prompt Ensembling in Text-Image Models
James Urquhart Allingham, Jie Ren, Michael W Dusenberry +5
Contrastively trained text-image models have the remarkable ability to perform zero-shot classification, that is, classifying previously unseen images into categories that the mode…
Addressing Bias in Active Learning with Depth Uncertainty Networks... or Not
Chelsea Murray, James U. Allingham, Javier Antorán +1
Farquhar et al. [2021] show that correcting for active learning bias with underparameterised models leads to improved downstream performance. For overparameterised models such as N…
Depth Uncertainty Networks for Active Learning
Chelsea Murray, James U. Allingham, Javier Antorán +1
In active learning, the size and complexity of the training dataset changes over time. Simple models that are well specified by the amount of data available at the start of active…
Sparse MoEs meet Efficient Ensembles
James Urquhart Allingham, Florian Wenzel, Zelda E Mariet +10
Machine learning models based on the aggregated outputs of submodels, either at the activation or prediction levels, often exhibit strong performance compared to individual models.…
Bayesian Deep Learning via Subnetwork Inference
Erik Daxberger, Eric Nalisnick, James Urquhart Allingham +2
The Bayesian paradigm has the potential to solve core issues of deep neural networks such as poor calibration and data inefficiency. Alas, scaling Bayesian inference to large weigh…