no code implementations • 30 Jan 2024 • Lucile Ter-Minassian, Sahra Ghalebikesabi, Karla Diaz-Ordaz, Chris Holmes
With the adoption of machine learning into routine clinical practice comes the need for Explainable AI methods tailored to medical applications.
no code implementations • 11 Jul 2023 • Jack Jewson, Sahra Ghalebikesabi, Chris Holmes
To ameliorate this, we propose $\beta$D-Bayes, a posterior sampling scheme from a generalised posterior targeting the minimisation of the $\beta$-divergence between the model and the data generating process.
no code implementations • NeurIPS 2023 • Veit David Wild, Sahra Ghalebikesabi, Dino Sejdinovic, Jeremias Knoblauch
We establish the first mathematically rigorous link between Bayesian, variational Bayesian, and ensemble methods.
no code implementations • 26 Apr 2023 • Melanie F. Pradier, Niranjani Prasad, Paidamoyo Chapfuwa, Sahra Ghalebikesabi, Max Ilse, Steven Woodhouse, Rebecca Elyanow, Javier Zazo, Javier Gonzalez, Julia Greissl, Edward Meeds
Recent advances in immunomics have shown that T-cell receptor (TCR) signatures can accurately predict active or recent infection by leveraging the high specificity of TCR binding to disease antigens.
no code implementations • 27 Feb 2023 • Sahra Ghalebikesabi, Leonard Berrada, Sven Gowal, Ira Ktena, Robert Stanforth, Jamie Hayes, Soham De, Samuel L. Smith, Olivia Wiles, Borja Balle
By privately fine-tuning ImageNet pre-trained diffusion models with more than 80M parameters, we obtain SOTA results on CIFAR-10 and Camelyon17 in terms of both FID and the accuracy of downstream classifiers trained on synthetic data.
no code implementations • 13 Jun 2022 • Sahra Ghalebikesabi, Chris Holmes, Edwin Fong, Brieuc Lehmann
In the context of density estimation, the standard nonparametric Bayesian approach is to target the posterior predictive of the Dirichlet process mixture model.
no code implementations • 24 Aug 2021 • Sahra Ghalebikesabi, Harrison Wilde, Jack Jewson, Arnaud Doucet, Sebastian Vollmer, Chris Holmes
Increasing interest in privacy-preserving machine learning has led to new and evolved approaches for generating private synthetic data from undisclosed real data.
1 code implementation • NeurIPS 2021 • Sahra Ghalebikesabi, Lucile Ter-Minassian, Karla Diaz-Ordaz, Chris Holmes
Empirically, we observe that Neighbourhood Shapley values identify meaningful sparse feature relevance attributions that provide insight into local model behaviour, complimenting conventional Shapley analysis.
1 code implementation • 5 Mar 2021 • Sahra Ghalebikesabi, Rob Cornish, Luke J. Kelly, Chris Holmes
We propose a variational autoencoder architecture to model both ignorable and nonignorable missing data using pattern-set mixtures as proposed by Little (1993).