Lifted Relational Variational Inference
This work addresses inference difficulties in hybrid models for applications like robotics and finance, representing an incremental improvement through a novel method for a known bottleneck.
The paper tackles the challenge of inference in large-scale hybrid continuous-discrete models by introducing an efficient relational variational inference algorithm that factors complex probability models into simpler variational ones, achieving close-to-optimal performance while maintaining relational structure during inference.
Hybrid continuous-discrete models naturally represent many real-world applications in robotics, finance, and environmental engineering. Inference with large-scale models is challenging because relational structures deteriorate rapidly during inference with observations. The main contribution of this paper is an efficient relational variational inference algorithm that factors largescale probability models into simpler variational models, composed of mixtures of iid (Bernoulli) random variables. The algorithm takes probability relational models of largescale hybrid systems and converts them to a close-to-optimal variational models. Then, it efficiently calculates marginal probabilities on the variational models by using a latent (or lifted) variable elimination or a lifted stochastic sampling. This inference is unique because it maintains the relational structure upon individual observations and during inference steps.