OneFlowSBI: One Model, Many Queries for Simulation-Based Inference

TL;DR

OneFlowSBI introduces a unified, query-aware generative model for simulation-based inference that efficiently supports multiple inference tasks without retraining, demonstrating competitive performance on benchmarks and real-world problems.

Contribution

It presents a novel unified framework that learns a single flow-matching model capable of handling diverse inference tasks in simulation-based inference.

Findings

Competitive performance against state-of-the-art methods

Efficient sampling with few ODE steps

Robust under noisy and partial observations

Abstract

We introduce \textit{OneFlowSBI}, a unified framework for simulation-based inference that learns a single flow-matching generative model over the joint distribution of parameters and observations. Leveraging a query-aware masking distribution during training, the same model supports multiple inference tasks, including posterior sampling, likelihood estimation, and arbitrary conditional distributions, without task-specific retraining. We evaluate \textit{OneFlowSBI} on ten benchmark inference problems and two high-dimensional real-world inverse problems across multiple simulation budgets. \textit{OneFlowSBI} is shown to deliver competitive performance against state-of-the-art generalized inference solvers and specialized posterior estimators, while enabling efficient sampling with few ODE integration steps and remaining robust under noisy and partially observed data.