一个模型搞定多种推断任务，无需重新训练
OneFlowSBI: One Model, Many Queries for Simulation-Based Inference
- 用统一的流匹配模型联合学习参数与观测分布
- 支持后验采样、似然估计等任务，少量ODE步数即可高效采样
- 适合需要多任务灵活推断的科研与工程场景
我们提出OneFlowSBI，一种统一的模拟推断框架，通过在训练中引入查询感知掩码分布，使单一流匹配生成模型能够学习参数与观测的联合分布。该模型无需任务特定微调即可支持后验采样、似然估计及任意条件分布推断。我们在十个基准推断问题和两个高维真实世界反问题上评估了该方法，覆盖多种模拟预算。实验表明，OneFlowSBI在性能上可媲美最先进通用推断求解器和专用后验估计器，同时具备少步数ODE积分下的高效采样能力，并在噪声数据和部分可观测条件下保持鲁棒性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。