Approximate Decentralized Bayesian Inference
This work addresses the challenge of scalable Bayesian inference for distributed learning agents, though it appears incremental as it builds on existing variational and decentralized approaches.
The paper tackles the problem of performing Bayesian inference in decentralized networks by introducing an approximate method that addresses broken dependencies in local posteriors, resulting in improved computational performance and predictive test likelihood over prior methods.
This paper presents an approximate method for performing Bayesian inference in models with conditional independence over a decentralized network of learning agents. The method first employs variational inference on each individual learning agent to generate a local approximate posterior, the agents transmit their local posteriors to other agents in the network, and finally each agent combines its set of received local posteriors. The key insight in this work is that, for many Bayesian models, approximate inference schemes destroy symmetry and dependencies in the model that are crucial to the correct application of Bayes' rule when combining the local posteriors. The proposed method addresses this issue by including an additional optimization step in the combination procedure that accounts for these broken dependencies. Experiments on synthetic and real data demonstrate that the decentralized method provides advantages in computational performance and predictive test likelihood over previous batch and distributed methods.