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.
翻译:本文提出\textit{OneFlowSBI},一种用于仿真推断的统一框架,该框架通过流匹配生成模型学习参数与观测值的联合分布。通过在训练阶段引入查询感知的掩码分布,同一模型无需针对特定任务重新训练即可支持多种推断任务,包括后验采样、似然估计以及任意条件分布。我们在十个基准推断问题和两个高维现实世界逆问题上,针对多种仿真计算预算评估了\textit{OneFlowSBI}的性能。实验表明,\textit{OneFlowSBI}在少量常微分方程积分步数下即可实现高效采样,且在噪声数据和部分观测数据下保持鲁棒性,其性能与最先进的广义推断求解器及专用后验估计器相比具有竞争力。