Composing graphical models with neural networks for structured representations and fast inference
| Autor: | Johnson, Matthew J., Duvenaud, David, Wiltschko, Alexander B., Datta, Sandeep R., Adams, Ryan P. |
|---|---|
| Rok vydání: | 2016 |
| Předmět: | |
| Druh dokumentu: | Working Paper |
| Popis: | We propose a general modeling and inference framework that composes probabilistic graphical models with deep learning methods and combines their respective strengths. Our model family augments graphical structure in latent variables with neural network observation models. For inference, we extend variational autoencoders to use graphical model approximating distributions with recognition networks that output conjugate potentials. All components of these models are learned simultaneously with a single objective, giving a scalable algorithm that leverages stochastic variational inference, natural gradients, graphical model message passing, and the reparameterization trick. We illustrate this framework with several example models and an application to mouse behavioral phenotyping. Comment: v5 fixes tex compilation bugs and also a math bug in the statement and proof of Prop. 4.1 (and D.3). v4 adds two paragraphs to the related work section and fixes typos in the appendices. v3 fixes some typos in the appendices. v2 is a rewrite from v1 to be more readable and to include detailed appendices |
| Databáze: | arXiv |
| Externí odkaz: |
|