Path-Gradient Estimators for Continuous Normalizing Flows
This work addresses a bottleneck in variational inference for researchers and practitioners by enabling more accurate gradient estimation in complex models, though it is incremental as it extends an existing method to a broader class.
The authors tackled the limitation of path-gradient estimators being restricted to simple Gaussian variational distributions by proposing a path-gradient estimator for continuous normalizing flows, a more expressive variational family, and demonstrated its superior performance empirically.
Recent work has established a path-gradient estimator for simple variational Gaussian distributions and has argued that the path-gradient is particularly beneficial in the regime in which the variational distribution approaches the exact target distribution. In many applications, this regime can however not be reached by a simple Gaussian variational distribution. In this work, we overcome this crucial limitation by proposing a path-gradient estimator for the considerably more expressive variational family of continuous normalizing flows. We outline an efficient algorithm to calculate this estimator and establish its superior performance empirically.