论文标题
循环中的域专家近似贝叶斯计算
Approximate Bayesian Computation with Domain Expert in the Loop
论文作者
论文摘要
近似贝叶斯计算（ABC）是具有棘手可能性函数模型的流行无可能推理方法。由于ABC方法通常依赖于比较观察到的数据和模拟数据的摘要统计数据，因此统计数据的选择至关重要。此选择涉及信息丢失和降低维度之间的权衡，并且通常是根据领域知识确定的。但是，手工制作和选择合适的统计数据是一项艰巨的任务，涉及多个试用步骤。在这项工作中，我们引入了一种积极的ABC统计选择方法，可大大减少域专家的工作。通过参与专家，我们能够处理拼写错误的模型，这与现有的减小方法不同。此外，与现有方法相比，在模拟预算有限时，经验结果比现有方法更好。
Approximate Bayesian computation (ABC) is a popular likelihood-free inference method for models with intractable likelihood functions. As ABC methods usually rely on comparing summary statistics of observed and simulated data, the choice of the statistics is crucial. This choice involves a trade-off between loss of information and dimensionality reduction, and is often determined based on domain knowledge. However, handcrafting and selecting suitable statistics is a laborious task involving multiple trial-and-error steps. In this work, we introduce an active learning method for ABC statistics selection which reduces the domain expert's work considerably. By involving the experts, we are able to handle misspecified models, unlike the existing dimension reduction methods. Moreover, empirical results show better posterior estimates than with existing methods, when the simulation budget is limited.
