Balancing Simulation-based Inference for Conservative Posteriors
This work addresses a major concern in simulation-based inference for researchers and practitioners by mitigating overconfidence in posterior approximations, though it is incremental as it builds on existing balancing methods.
The paper tackles the problem of overconfident posterior approximations in simulation-based inference by extending balancing, previously limited to neural ratio estimation, to any algorithm providing a posterior density, including neural posterior estimation and contrastive neural ratio estimation, and shows empirically that balanced versions produce conservative posteriors on various benchmarks.
Conservative inference is a major concern in simulation-based inference. It has been shown that commonly used algorithms can produce overconfident posterior approximations. Balancing has empirically proven to be an effective way to mitigate this issue. However, its application remains limited to neural ratio estimation. In this work, we extend balancing to any algorithm that provides a posterior density. In particular, we introduce a balanced version of both neural posterior estimation and contrastive neural ratio estimation. We show empirically that the balanced versions tend to produce conservative posterior approximations on a wide variety of benchmarks. In addition, we provide an alternative interpretation of the balancing condition in terms of the $χ^2$ divergence.