Inductive Domain Transfer In Misspecified Simulation-Based Inference

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

Keywords: AI4Science, SBI, Domain transfer, sim2real

TL;DR: We propose a semi-supervised domain transfer approach for bridging the sim2real gap in simulation-based inference, leveraging mini-batch optimal transport for scalable, inductive posterior approximation.

Abstract:

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 domain transfer process that combines semi-supervised calibration with optimal transport (OT)-based distribution alignment. However, RoPE operates in a fully transductive setting, requiring access to a batch of test samples at inference time, which limits scalability and generalization. We propose a fully inductive and amortized SBI framework that integrates calibration and distributional alignment into a single, end-to-end trainable model. Our method leverages mini-batch OT with a closed-form coupling to align real and simulated observations that correspond to the same latent parameters, using both paired calibration data and unpaired samples. A conditional normalizing flow is then trained to approximate the OT-induced posterior, enabling efficient inference without simulation access at test time.
Across a range of synthetic and real-world benchmarks--including complex medical biomarker estimation--our approach matches or exceeds the performance of RoPE, while offering improved scalability and applicability in challenging, misspecified environments.

Primary Area: Machine learning for sciences (e.g. climate, health, life sciences, physics, social sciences)

Submission Number: 22023