Likelihood-Free Inference in State-Space Models with Unknown Dynamics
This addresses a bottleneck in likelihood-free inference for state-space models, enabling more efficient inference in scenarios with limited simulations and undefined dynamics, though it appears incremental as it builds on existing LFI techniques.
The paper tackles the problem of state inference in state-space models when simulations are expensive and transition dynamics are unknown, proposing a method that estimates dynamics and uses state predictions as proposals, resulting in significant accuracy improvements in experiments with non-stationary user models.
Likelihood-free inference (LFI) has been successfully applied to state-space models, where the likelihood of observations is not available but synthetic observations generated by a black-box simulator can be used for inference instead. However, much of the research up to now have been restricted to cases, in which a model of state transition dynamics can be formulated in advance and the simulation budget is unrestricted. These methods fail to address the problem of state inference when simulations are computationally expensive and the Markovian state transition dynamics are undefined. The approach proposed in this manuscript enables LFI of states with a limited number of simulations by estimating the transition dynamics, and using state predictions as proposals for simulations. In the experiments with non-stationary user models, the proposed method demonstrates significant improvement in accuracy for both state inference and prediction, where a multi-output Gaussian process is used for LFI of states, and a Bayesian Neural Network as a surrogate model of transition dynamics.