Timezone: »

Approximate Bayesian Computation with Domain Expert in the Loop
Ayush Bharti · Louis Filstroff · Samuel Kaski

Wed Jul 20 10:35 AM -- 10:40 AM (PDT) @ None

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.

Author Information

Ayush Bharti (Aalto University)
Louis Filstroff (Aalto University)
Samuel Kaski (Aalto University and University of Manchester)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors