A General Method for Amortizing Variational Filtering

Abstract

We introduce the variational filtering EM algorithm, a simple, general-purpose method for performing variational inference in dynamical latent variable models using information from only past and present variables, i.e. filtering. The algorithm is derived from the variational objective in the filtering setting and consists of an optimization procedure at each time step. By performing each inference optimization procedure with an iterative amortized inference model, we obtain a computationally efficient implementation of the algorithm, which we call amortized variational filtering. We present experiments demonstrating that this general-purpose method improves performance across several deep dynamical latent variable models.

arXiv commentAdvances in Neural Information Processing Systems (NIPS) 2018

Cited by in corpus (8)

• Multi-Object Representation Learning with Iterative Variational Inference
• Entity Abstraction in Visual Model-Based Reinforcement Learning
• Disentangled State Space Representations
• Improving Sequential Latent Variable Models with Autoregressive Flows
• Iterative Amortized Policy Optimization
• Control as Hybrid Inference
• Relational State-Space Model for Stochastic Multi-Object Systems
• Online Variational Filtering and Parameter Learning