Circuit representations are becoming the lingua franca to express and reason about tractable generative and discriminative models. In this paper, we show how complex inference scenarios for these models that commonly arise in machine learning--from computing the expectations of decision tree ensembles to information-theoretic divergencesofsum-product networks--can berepresented interms oftractable modular operations overcircuits.

However, using these 50B+ models requires high-end hardware, making them inaccessible to most researchers.

In the BAI, the learner needs to pull arms efficiently for better identification.

Existing work has examined these effects asymptotically, but implementable finite sample results are needed in practice so that users can specify privacy budgets in advance and implement samplers with exact privacy guarantees.