Bayesian Learning for Dynamic Inference
This work provides a unifying meta-problem that can encompass various machine learning tasks like supervised, imitation, and reinforcement learning, potentially offering insights across a broad spectrum of ML problems.
The authors tackled the dynamic inference problem, where future values of an estimated quantity depend on current estimates, by formulating Bayesian learning rules for both offline and online settings to minimize inference loss.
The traditional statistical inference is static, in the sense that the estimate of the quantity of interest does not affect the future evolution of the quantity. In some sequential estimation problems however, the future values of the quantity to be estimated depend on the estimate of its current value. This type of estimation problems has been formulated as the dynamic inference problem. In this work, we formulate the Bayesian learning problem for dynamic inference, where the unknown quantity-generation model is assumed to be randomly drawn according to a random model parameter. We derive the optimal Bayesian learning rules, both offline and online, to minimize the inference loss. Moreover, learning for dynamic inference can serve as a meta problem, such that all familiar machine learning problems, including supervised learning, imitation learning and reinforcement learning, can be cast as its special cases or variants. Gaining a good understanding of this unifying meta problem thus sheds light on a broad spectrum of machine learning problems as well.