Kernel Implicit Variational Inference
Recent progress in variational inference has paid much attention to the flexibility of variational posteriors. One promising direction is to use implicit distributions, i.e., distributions without tractable densities as the variational posterior. However, existing methods on implicit posteriors still face challenges of noisy estimation and computational infeasibility when applied to models with high-dimensional latent variables. In this paper, we present a new approach named Kernel Implicit Variational Inference 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.
Code (0)
등록된 구현이 없습니다.
Tasks
General ClassificationregressionVariational InferenceSimilar Papers 제목 키워드 기반
A Kernel Approach for Semi-implicit Variational Inference
Semi-implicit variational inference (SIVI) enhances the expressiveness of variational families through hierarchical semi-implicit distributions, but the intractability of their densities makes standard ELBO-based optimiz…
Bayesian InferenceSemi-Implicit Variational Inference via Kernelized Path Gradient Descent
Semi-implicit variational inference (SIVI) is a powerful framework for approximating complex posterior distributions, but training with the Kullback-Leibler (KL) divergence can be challenging due to high variance and bia…
Variational InferenceKernel Semi-Implicit Variational Inference
Semi-implicit variational inference (SIVI) extends traditional variational families with semi-implicit distributions defined in a hierarchical manner. Due to the intractable densities of semi-implicit distributions, clas…
Bayesian InferenceVariational InferenceDoubly Semi-Implicit Variational Inference
We extend the existing framework of semi-implicit variational inference (SIVI) and introduce doubly semi-implicit variational inference (DSIVI), a way to perform variational inference and learning when both the approxima…
Variational InferenceParticle Semi-Implicit Variational Inference
Semi-implicit variational inference (SIVI) enriches the expressiveness of variational families by utilizing a kernel and a mixing distribution to hierarchically define the variational distribution. Existing SIVI methods …
Variational Inference