Two Methods For Wild Variational Inference
arXiv:1612.00081
Abstract
Variational inference provides a powerful tool for approximate probabilistic in- ference on complex, structured models. Typical variational inference methods, however, require to use inference networks with computationally tractable proba- bility density functions. This largely limits the design and implementation of vari- ational inference methods. We consider wild variational inference methods that do not require tractable density functions on the inference networks, and hence can be applied in more challenging cases. As an example of application, we treat stochastic gradient Langevin dynamics (SGLD) as an inference network, and use our methods to automatically adjust the step sizes of SGLD, yielding significant improvement over the hand-designed step size schemes
References in corpus (8)
- Auto-Encoding Variational Bayes
- Variational Inference with Normalizing Flows
- Markov Chain Monte Carlo and Variational Inference: Bridging the Gap
- Measuring Sample Quality with Stein's Method
- Learning to Draw Samples: With Application to Amortized MLE for Generative Adversarial Learning
- Operator Variational Inference
- A Variational Analysis of Stochastic Gradient Algorithms
- Inference Networks for Sequential Monte Carlo in Graphical Models