Learning Deep Generative Models with Annealed Importance Sampling
This work addresses a fundamental challenge in machine learning for researchers and practitioners by providing an incremental improvement in model accuracy for deep generative models.
The paper tackles the problem of learning deep generative models by proposing an approach using annealed importance sampling, which bridges variational inference and Markov chain Monte Carlo methods, and shows it yields better density models than importance weighted auto-encoders while trading computation for accuracy without increasing memory cost.
Variational inference (VI) and Markov chain Monte Carlo (MCMC) are two main approximate approaches for learning deep generative models by maximizing marginal likelihood. In this paper, we propose using annealed importance sampling for learning deep generative models. Our proposed approach bridges VI with MCMC. It generalizes VI methods such as variational auto-encoders and importance weighted auto-encoders (IWAE) and the MCMC method proposed in (Hoffman, 2017). It also provides insights into why running multiple short MCMC chains can help learning deep generative models. Through experiments, we show that our approach yields better density models than IWAE and can effectively trade computation for model accuracy without increasing memory cost.