12 citations · 43 across the 11 of their papers we have counts for
11 papers
DeepClean: Machine Unlearning on the Cheap by Resetting Privacy Sensitive Weights using the Fisher Diagonal
Jiaeli Shi, Najah Ghalyan, Kostis Gourgoulias +2
Machine learning models trained on sensitive or private data can inadvertently memorize and leak that information. Machine unlearning seeks to retroactively remove such details fro…
Estimating class separability of text embeddings with persistent homology
Kostis Gourgoulias, Najah Ghalyan, Maxime Labonne +3
This paper introduces an unsupervised method to estimate the class separability of text datasets from a topological point of view. Using persistent homology, we demonstrate how tra…
Learning medical triage from clinicians using Deep Q-Learning
Albert Buchard, Baptiste Bouvier, Giulia Prando +10
Medical Triage is of paramount importance to healthcare systems, allowing for the correct orientation of patients and allocation of the necessary resources to treat them adequately…
Masking schemes for universal marginalisers
Divya Gautam, Maria Lomeli, Kostis Gourgoulias +2
We consider the effect of structure-agnostic and structure-dependent masking schemes when training a universal marginaliser (arXiv:1711.00695) in order to learn conditional distrib…
Universal Marginaliser for Deep Amortised Inference for Probabilistic Programs
Robert Walecki, Kostis Gourgoulias, Adam Baker +7
Probabilistic programming languages (PPLs) are powerful modelling tools which allow to formalise our knowledge about the world and reason about its inherent uncertainty. Inference…
MultiVerse: Causal Reasoning using Importance Sampling in Probabilistic Programming
Yura Perov, Logan Graham, Kostis Gourgoulias +4
We elaborate on using importance sampling for causal reasoning, in particular for counterfactual inference. We show how this can be implemented natively in probabilistic programmin…
Universal Marginalizer for Amortised Inference and Embedding of Generative Models
Robert Walecki, Albert Buchard, Kostis Gourgoulias +6
Probabilistic graphical models are powerful tools which allow us to formalise our knowledge about the world and reason about its inherent uncertainty. There exist a considerable nu…
A Universal Marginalizer for Amortized Inference in Generative Models
Laura Douglas, Iliyan Zarov, Konstantinos Gourgoulias +6
We consider the problem of inference in a causal generative model where the set of available observations differs between data instances. We show how combining samples drawn from t…
How biased is your model? Concentration Inequalities, Information and Model Bias
Konstantinos Gourgoulias, Markos A. Katsoulakis, Luc Rey-Bellet +1
We derive tight and computable bounds on the bias of statistical estimators, or more generally of quantities of interest, when evaluated on a baseline model P rather than on the ty…
Information Criteria for quantifying loss of reversibility in parallelized KMC
Konstantinos Gourgoulias, Markos A. Katsoulakis, Luc Rey-Bellet
Parallel Kinetic Monte Carlo (KMC) is a potent tool to simulate stochastic particle systems efficiently. However, despite literature on quantifying domain decomposition errors of t…
Information metrics for long-time errors in splitting schemes for stochastic dynamics and parallel KMC
Konstantinos Gourgoulias, Markos A. Katsoulakis, Luc Rey-Bellet
We propose an information-theoretic approach to analyze the long-time behavior of numerical splitting schemes for stochastic dynamics, focusing primarily on Parallel Kinetic Monte…