/implicit-variational-inference

The collection of recent papers about variational inference

Advanced-variational-inference-paper

The collection of recent papers about variational inference

Variational Inference using Implicit Prior and/or Posterior Distributions.

  1. Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks
  2. Variational Inference Using Implicit Distributions
  3. Hierarchical Implicit Models and Likelihood-Free Variational Inference
  4. Kernel Implicit Variational Inference
  5. Semi-Implicit Variational Inference
  6. Unbiased Implicit Variational Inference
  7. Doubly Semi-Implicit Variational Inference
  8. Stein Neural Sampler

Variational Inference with Alternative Divergences

  1. Black-Box α-Divergence Minimization
  2. Rényi Divergence Variational Inference
  3. Operator Variational Inference
  4. Variational Inference via χ Upper Bound Minimization
  5. Variational Inference based on Robust Divergences
  6. Alpha-Beta Divergence For Variational Inference
  7. Wasserstein Variational Inference
  8. Stein Neural Sampler
  9. Variational Inference with Tail-adaptive f-Divergence
  10. Adversarial α-divergence Minimization for Bayesian Approximate Inference
  11. Refined α-Divergence Variational Inference via Rejection Sampling

Variational Inference with Normalizing Flows

  1. Variational Inference with Normalizing Flows
  2. Improved Variational Inference with Inverse Autoregressive Flow
  3. Improving Variational Auto-Encoders using Householder Flow
  4. Variational Inference with Orthogonal Normalizing Flows
  5. Improving Variational Auto-Encoders using Convex Combination Linear Inverse Autoregressive Flow
  6. Convolutional Normalizing Flows
  7. Sylvester Normalizing Flows for Variational Inference

Partilcle-based Variational Inference and Applications

  1. Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm
  2. Stein Variational Policy Gradient
  3. VAE Learning via Stein Variational Gradient Descent
  4. Stein Variational Adaptive Importance Sampling
  5. Stein Variational Gradient Descent as Gradient Flow
  6. Learning to Draw Samples with Amortized Stein Variational Gradient Descent
  7. Message Passing Stein Variational Gradient Descent
  8. Stein Variational Message Passing for Continuous Graphical Models
  9. Particle Optimization in Stochastic Gradient MCMC
  10. Riemannian Stein Variational Gradient Descent for Bayesian Inference
  11. Stein Points
  12. Bayesian Posterior Approximation via Greedy Particle Optimization
  13. A Unified Particle-optimization Framework for Scalable Bayesian Sampling
  14. Stein Variational Gradient Descent Without Gradient
  15. A Stein variational Newton method
  16. Accelerated First-order Methods on the Wasserstein Space for Bayesian Inference
  17. Stochastic Particle-optimization Sampling and the Non-asymptotic Convergence Theory
  18. Stein Variational Gradient Descent as Moment Matching
  19. Wasserstein Variational Gradient Descent: From Semi-discrete Optimal Transport to Ensemble Variational Inference
  20. Variance Reduction in Stochastic Particle-optimization Sampling
  21. Projected Stein Variational Newton: A Fast and Scalable Bayesian Inference Method in High Dimensions
  22. Understanding MCMC Dynamics as Flows on the Wasserstein Space
  23. A Stochastic Version of Stein Variational Gradient Descent for Efficient Sampling
  24. Stein Point Markov Chain Monte Carlo
  25. Nonlinear Stein Variational Gradient Descent for Learning Diversified Mixture Models
  26. Quantile Stein Variational Gradient Descent for Batch Bayesian Optimization
  27. Stein Vriational Gradient Descent with Matrix-valued Kernels