Antoine Wehenkel — accepted AI-conference papers

2025

Addressing Misspecification in Simulation-based Inference through Data-driven Calibration

Antoine Wehenkel, Juan L. Gamella, Ozan Sener, Jens Behrmann, Guillermo Sapiro, Joern-Henrik Jacobsen +1

ICML 2025oral

Driven by steady progress in deep generative modeling, simulation-based inference (SBI) has emerged as the workhorse for inferring the parameters of stochastic simulators. However, recent work has demonstrated that model misspecification can harm SBI's reliability, preventing its adoption in importa…

Cited by 12 Source ↗PDF ↗Scholar ↗

2025

Inductive Domain Transfer In Misspecified Simulation-Based Inference

Ortal Senouf, Antoine Wehenkel, Cédric Vincent-Cuaz, Emmanuel Abbe, Pascal Frossard

NeurIPS 2025poster

Simulation-based inference (SBI) of latent parameters in physical systems is often hindered by model misspecification--the mismatch between simulated and real-world observations caused by inherent modeling simplifications. RoPE, a recent SBI approach, addresses this challenge through a two-stage dom…

Cited by 0 Source ↗Scholar ↗

2023

Calibrating Neural Simulation-Based Inference with Differentiable Coverage Probability

Maciej Falkiewicz, Naoya Takeishi, Imahn Shekhzadeh, Antoine Wehenkel, Arnaud Delaunoy, Gilles Louppe +1

NeurIPS 2023poster

Bayesian inference allows expressing the uncertainty of posterior belief under a probabilistic model given prior information and the likelihood of the evidence. Predominantly, the likelihood function is only implicitly established by a simulator posing the need for simulation-based inference (SBI).…

Cited by 8 Source ↗PDF ↗code ↗Scholar ↗

2022

Towards Reliable Simulation-Based Inference with Balanced Neural Ratio Estimation

Arnaud Delaunoy, Joeri Hermans, François Rozet, Antoine Wehenkel, Gilles Louppe

NeurIPS 2022accept

Modern approaches for simulation-based inference build upon deep learning surrogates to enable approximate Bayesian inference with computer simulators. In practice, the estimated posteriors' computational faithfulness is, however, rarely guaranteed. For example, Hermans et al., 2021 have shown that…

Cited by 34 Source ↗PDF ↗code ↗Scholar ↗

2021

Graphical Normalizing Flows

Antoine Wehenkel, Gilles Louppe

AISTATS 2021poster

Normalizing flows model complex probability distributions by combining a base distribution with a series of bijective neural networks. State-of-the-art architectures rely on coupling and autoregressive transformations to lift up invertible functions from scalars to vectors. In this work, we revisit…

Cited by 42 Source ↗PDF ↗code ↗Scholar ↗

2021

Neural Empirical Bayes: Source Distribution Estimation and its Applications to Simulation-Based Inference

Maxime Vandegar, Michael Kagan, Antoine Wehenkel, Gilles Louppe

AISTATS 2021poster

We revisit g-modeling empirical Bayes in the absence of a tractable likelihood function, as is typical in scientific domains relying on computer simulations. We investigate how the empirical Bayesian can make use of neural density estimators first to use all noise-corrupted observations to estimate…

Cited by 36 Source ↗PDF ↗code ↗Scholar ↗

2019

Unconstrained Monotonic Neural Networks

Antoine Wehenkel, Gilles Louppe

NeurIPS 2019poster

Monotonic neural networks have recently been proposed as a way to define invertible transformations. These transformations can be combined into powerful autoregressive flows that have been shown to be universal approximators of continuous probability distributions. Architectures that ensure monotoni…

Cited by 221 Source ↗PDF ↗code ↗Scholar ↗