Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Two Methods for Wild Variational Inference
Qiang Liu, Yihao Feng
Nov 04, 2016 (modified: Jan 24, 2017)ICLR 2017 conference submissionreaders: everyone
Abstract:Variational inference provides a powerful tool for approximate probabilistic inference on complex, structured models. Typical variational inference methods, however, require to use inference networks with computationally tractable probability density functions. This largely limits the design and implementation of variational 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 to maximize its convergence speed, significantly outperforming the hand-designed step size schemes.
Enter your feedback below and we'll get back to you as soon as possible.