1 code implementation • 27 Aug 2024 • Arnaud Delaunoy, Maxence de la Brassinne Bonardeaux, Siddharth Mishra-Sharma, Gilles Louppe
We show that Bayesian neural networks produce informative and well-calibrated posterior estimates with only a few hundred simulations.
1 code implementation • NeurIPS 2023 • Maciej Falkiewicz, Naoya Takeishi, Imahn Shekhzadeh, Antoine Wehenkel, Arnaud Delaunoy, Gilles Louppe, Alexandros Kalousis
Bayesian inference allows expressing the uncertainty of posterior belief under a probabilistic model given prior information and the likelihood of the evidence.
1 code implementation • 21 Apr 2023 • Arnaud Delaunoy, Benjamin Kurt Miller, Patrick Forré, Christoph Weniger, Gilles Louppe
We show empirically that the balanced versions tend to produce conservative posterior approximations on a wide variety of benchmarks.
1 code implementation • 29 Aug 2022 • Arnaud Delaunoy, Joeri Hermans, François Rozet, Antoine Wehenkel, Gilles Louppe
In this work, we introduce Balanced Neural Ratio Estimation (BNRE), a variation of the NRE algorithm designed to produce posterior approximations that tend to be more conservative, hence improving their reliability, while sharing the same Bayes optimal solution.
1 code implementation • 30 Dec 2021 • Arnaud Delaunoy, Gilles Louppe
Anchored ensembles approximate the posterior by training an ensemble of neural networks on anchored losses designed for the optima to follow the Bayesian posterior.
4 code implementations • 13 Oct 2021 • Joeri Hermans, Arnaud Delaunoy, François Rozet, Antoine Wehenkel, Volodimir Begy, Gilles Louppe
We present extensive empirical evidence showing that current Bayesian simulation-based inference algorithms can produce computationally unfaithful posterior approximations.
no code implementations • 24 Oct 2020 • Arnaud Delaunoy, Antoine Wehenkel, Tanja Hinderer, Samaya Nissanke, Christoph Weniger, Andrew R. Williamson, Gilles Louppe
Gravitational waves from compact binaries measured by the LIGO and Virgo detectors are routinely analyzed using Markov Chain Monte Carlo sampling algorithms.