Implicit Variational Inference with Kernel Density Ratio Fitting
By Jiaxin Shi, Jun Zhu. 2017
3 citations recorded by the source corpus.
Recent progress in variational inference has paid much attention to the flexibility of variational posteriors. Work has been done to use implicit distributions, i.e., distributions without tractable likelihoods as the variational posterior. However, existing methods on implicit posteriors still face challenges of noisy estimation and can hardly scale to high-dimensional latent variable models. In this paper, we present an implicit variational inference approach with kernel density ratio fitting that addresses these challenges. As far as we know, for the first time implicit variational inference is successfully applied to Bayesian neural networks, which shows promising results on both regression and classification tasks.
Subfields: Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
Citations in the corpus
- Semi-Implicit Variational Inference (2018, background): “…the variational family that Q belongs to, there has been significant recent interest in defining Q with an implicit model, which makes the PDF of Q become intractable (Husz´ar, 2017; Mohamed & Lakshminarayanan, 2016; Tran et al., 2017; Li & Turner, 2017; Mescheder et al., 2017; Shi et al., 2017).”