research
∙
06/05/2023
Towards Anytime Classification in Early-Exit Architectures by Enforcing Conditional Monotonicity
Modern predictive models are often deployed to environments in which com...
share
research
∙
02/13/2023
A Simple Zero-shot Prompt Weighting Technique to Improve Prompt Ensembling in Text-Image Models
Contrastively trained text-image models have the remarkable ability to p...
research
∙
06/17/2022
Adapting the Linearised Laplace Model Evidence for Modern Deep Learning
The linearised Laplace method for estimating model uncertainty has recei...
research
∙
10/07/2021
Sparse MoEs meet Efficient Ensembles
Machine learning models based on the aggregated outputs of submodels, ei...
research
∙
10/28/2020
Expressive yet Tractable Bayesian Deep Learning via Subnetwork Inference
The Bayesian paradigm has the potential to solve some of the core issues...
research
∙
06/15/2020
Depth Uncertainty in Neural Networks
Existing methods for estimating uncertainty in deep learning tend to req...
research
∙
02/06/2020