The collection of recent papers about variational inference
- Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks
- Variational Inference Using Implicit Distributions
- Hierarchical Implicit Models and Likelihood-Free Variational Inference
- Kernel Implicit Variational Inference
- Semi-Implicit Variational Inference
- Unbiased Implicit Variational Inference
- Doubly Semi-Implicit Variational Inference
- Stein Neural Sampler
- Black-Box α-Divergence Minimization
- Rényi Divergence Variational Inference
- Operator Variational Inference
- Variational Inference via χ Upper Bound Minimization
- Variational Inference based on Robust Divergences
- Alpha-Beta Divergence For Variational Inference
- Wasserstein Variational Inference
- Stein Neural Sampler
- Variational Inference with Tail-adaptive f-Divergence
- Adversarial α-divergence Minimization for Bayesian Approximate Inference
- Refined α-Divergence Variational Inference via Rejection Sampling
- Variational Inference with Normalizing Flows
- Improved Variational Inference with Inverse Autoregressive Flow
- Improving Variational Auto-Encoders using Householder Flow
- Variational Inference with Orthogonal Normalizing Flows
- Improving Variational Auto-Encoders using Convex Combination Linear Inverse Autoregressive Flow
- Convolutional Normalizing Flows
- Sylvester Normalizing Flows for Variational Inference
- Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm
- Stein Variational Policy Gradient
- VAE Learning via Stein Variational Gradient Descent
- Stein Variational Adaptive Importance Sampling
- Stein Variational Gradient Descent as Gradient Flow
- Learning to Draw Samples with Amortized Stein Variational Gradient Descent
- Message Passing Stein Variational Gradient Descent
- Stein Variational Message Passing for Continuous Graphical Models
- Particle Optimization in Stochastic Gradient MCMC
- Riemannian Stein Variational Gradient Descent for Bayesian Inference
- Stein Points
- Bayesian Posterior Approximation via Greedy Particle Optimization
- A Unified Particle-optimization Framework for Scalable Bayesian Sampling
- Stein Variational Gradient Descent Without Gradient
- A Stein variational Newton method
- Accelerated First-order Methods on the Wasserstein Space for Bayesian Inference
- Stochastic Particle-optimization Sampling and the Non-asymptotic Convergence Theory
- Stein Variational Gradient Descent as Moment Matching
- Wasserstein Variational Gradient Descent: From Semi-discrete Optimal Transport to Ensemble Variational Inference
- Variance Reduction in Stochastic Particle-optimization Sampling
- Projected Stein Variational Newton: A Fast and Scalable Bayesian Inference Method in High Dimensions
- Understanding MCMC Dynamics as Flows on the Wasserstein Space
- A Stochastic Version of Stein Variational Gradient Descent for Efficient Sampling
- Stein Point Markov Chain Monte Carlo
- Nonlinear Stein Variational Gradient Descent for Learning Diversified Mixture Models
- Quantile Stein Variational Gradient Descent for Batch Bayesian Optimization