Hierarchical Variational Models
This addresses a central problem in machine learning for researchers using variational inference, offering a method to improve model expressiveness without sacrificing efficiency, though it appears incremental as it builds on existing black box techniques.
The paper tackles the challenge of specifying an expressive variational distribution while maintaining computational efficiency in variational inference, resulting in hierarchical variational models (HVMs) that capture complex structure and achieve higher fidelity to the posterior.
Black box variational inference allows researchers to easily prototype and evaluate an array of models. Recent advances allow such algorithms to scale to high dimensions. However, a central question remains: How to specify an expressive variational distribution that maintains efficient computation? To address this, we develop hierarchical variational models (HVMs). HVMs augment a variational approximation with a prior on its parameters, which allows it to capture complex structure for both discrete and continuous latent variables. The algorithm we develop is black box, can be used for any HVM, and has the same computational efficiency as the original approximation. We study HVMs on a variety of deep discrete latent variable models. HVMs generalize other expressive variational distributions and maintains higher fidelity to the posterior.