Search Results for author: Sahra Ghalebikesabi

Found 5 papers, 1 papers with code

Differentially Private Diffusion Models Generate Useful Synthetic Images

no code implementations27 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.

Image Generation Privacy Preserving

Quasi-Bayesian Nonparametric Density Estimation via Autoregressive Predictive Updates

no code implementations13 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.

Density Estimation

Mitigating Statistical Bias within Differentially Private Synthetic Data

no code implementations24 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.

Privacy Preserving

On Locality of Local Explanation Models

no code implementations 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.

Deep Generative Pattern-Set Mixture Models for Nonignorable Missingness

1 code implementation5 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).


Cannot find the paper you are looking for? You can Submit a new open access paper.