Flexible and accurate inference and learning for deep generative models
This work addresses the problem of accurate inference in deep generative models for researchers and practitioners, offering a novel approach but with incremental improvements over existing variational methods.
The paper tackles the challenge of learning hierarchical latent-variable generative models by introducing the distributed distributional code Helmholtz machine, which uses a flexible posterior representation and an extended wake-sleep algorithm, resulting in outperforming state-of-the-art methods on synthetic, natural image patch, and MNIST datasets.
We introduce a new approach to learning in hierarchical latent-variable generative models called the "distributed distributional code Helmholtz machine", which emphasises flexibility and accuracy in the inferential process. In common with the original Helmholtz machine and later variational autoencoder algorithms (but unlike adverserial methods) our approach learns an explicit inference or "recognition" model to approximate the posterior distribution over the latent variables. Unlike in these earlier methods, the posterior representation is not limited to a narrow tractable parameterised form (nor is it represented by samples). To train the generative and recognition models we develop an extended wake-sleep algorithm inspired by the original Helmholtz Machine. This makes it possible to learn hierarchical latent models with both discrete and continuous variables, where an accurate posterior representation is essential. We demonstrate that the new algorithm outperforms current state-of-the-art methods on synthetic, natural image patch and the MNIST data sets.