Towards Reliable Simulation-Based Inference with Balanced Neural Ratio Estimation (2022)
Averting A Crisis in Simulation-Based Inference (2021)
Towards constraining warm dark matter with stellar streams through neural simulation-based inference (2020)
Mining for Dark Matter Substructure: Inferring subhalo population properties from strong lenses with machine learning (2019)
Likelihood-free MCMC using Approximate Likelihood Ratios (2019)
Simulating Data Access Profiles of Computational Jobs in Data Grids (2019)
Adversarial Variational Optimization of Non-Differentiable Simulators (2018)
Gradient Energy Matching for Distributed Asynchronous Gradient Descent (2018)
Accumulated Gradient Normalization (M.Sc.) (2017)

Constraining the warm dark matter particle mass using machine learning and stellar streams (2020, Machine Learning @ STAR)
FFJORD: Free-from Continuous Dynamics for Scalable Reversible Generative Models (2019, INFO8004: Advanced Machine Learing
Likelihood-free MCMC (2019, PhD M'eating, ULg)

awflow (2021)
Amortized Experimental Design (2021)
Hypothesis (2019)
Warpdrive (2016)
Distributed Keras (2016)
Hadoop profiler (2016)