# Unbiased Implicit Variational Inference

arXiv: https://arxiv.org/abs/1808.02078 · HTML: https://mlsanity.com/paper/1808.02078/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Aug 2018.

## Built on by (most cited first, 30 of 33)

- [Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generation](https://mlsanity.com/paper/2404.04057/) (2024)
- [Semi-Implicit Variational Inference via Score Matching](https://mlsanity.com/paper/2308.10014/) (2023)
- [Learning to Jump: Thinning and Thickening Latent Counts for Generative Modeling](https://mlsanity.com/paper/2305.18375/) (2023)
- [On Out-of-distribution Detection with Energy-based Models](https://mlsanity.com/paper/2107.08785/) (2021)
- [Hierarchical Semi-Implicit Variational Inference with Application to Diffusion Model Acceleration](https://mlsanity.com/paper/2310.17153/) (2023)
- [A Practical Guide to Sample-based Statistical Distances for Evaluating Generative Models in Science](https://mlsanity.com/paper/2403.12636/) (2024)
- [A prior-based approximate latent Riemannian metric](https://mlsanity.com/paper/2103.05290/) (2021)
- [Efficient Semi-Implicit Variational Inference](https://mlsanity.com/paper/2101.06070/) (2021)
- [Quantum HyperNetworks: Training Binary Neural Networks in Quantum Superposition](https://mlsanity.com/paper/2301.08292/) (2023)
- [Kernel Semi-Implicit Variational Inference](https://mlsanity.com/paper/2405.18997/) (2024)
- [Particle Semi-Implicit Variational Inference](https://mlsanity.com/paper/2407.00649/) (2024)
- [Generative Bayesian Inference with GANs](https://mlsanity.com/paper/2208.12113/) (2022)
- [Neural Operator Variational Inference based on Regularized Stein Discrepancy for Deep Gaussian Processes](https://mlsanity.com/paper/2309.12658/) (2023)
- [Implicit Variational Inference for High-Dimensional Posteriors](https://mlsanity.com/paper/2310.06643/) (2023)
- [PAVI: Plate-Amortized Variational Inference](https://mlsanity.com/paper/2206.05111/) (2022)
- [Langevin Autoencoders for Learning Deep Latent Variable Models](https://mlsanity.com/paper/2209.07036/) (2022)
- [Fisher meets Feynman: score-based variational inference with a product of experts](https://mlsanity.com/paper/2510.21598/) (2025)
- [VFDS: Variational Foresight Dynamic Selection in Bayesian Neural Networks for Efficient Human Activity Recognition](https://mlsanity.com/paper/2204.00130/) (2022)
- [Master's Thesis: Out-of-distribution Detection with Energy-based Models](https://mlsanity.com/paper/2302.12002/) (2023)
- [Parameter Estimation in DAGs from Incomplete Data via Optimal Transport](https://mlsanity.com/paper/2305.15927/) (2023)
- [PAVI: Plate-Amortized Variational Inference](https://mlsanity.com/paper/2308.16022/) (2023)
- [Variational Bayesian Phylogenetic Inference with Semi-implicit Branch Length Distributions](https://mlsanity.com/paper/2408.05058/) (2024)
- [Semi-Implicit Functional Gradient Flow for Efficient Sampling](https://mlsanity.com/paper/2410.17935/) (2024)
- [A Kernel Approach for Semi-implicit Variational Inference](https://mlsanity.com/paper/2601.12023/) (2026)
- [Deep Probabilistic Graphical Modeling](https://mlsanity.com/paper/2104.12053/) (2021)
- [Bayesian Neural Network Inference via Implicit Models and the Posterior Predictive Distribution](https://mlsanity.com/paper/2209.02188/) (2022)
- [Pathwise Gradient Variance Reduction with Control Variates in Variational Inference](https://mlsanity.com/paper/2410.05753/) (2024)
- [Revisiting Unbiased Implicit Variational Inference](https://mlsanity.com/paper/2506.03839/) (2025)
- [Semi-Implicit Variational Inference via Kernelized Path Gradient Descent](https://mlsanity.com/paper/2506.05088/) (2025)
- [Continuous Semi-Implicit Models](https://mlsanity.com/paper/2506.06778/) (2025)

## Abstract (arXiv)

We develop unbiased implicit variational inference (UIVI), a method that expands the applicability of variational inference by defining an expressive variational family. UIVI considers an implicit variational distribution obtained in a hierarchical manner using a simple reparameterizable distribution whose variational parameters are defined by arbitrarily flexible deep neural networks. Unlike previous works, UIVI directly optimizes the evidence lower bound (ELBO) rather than an approximation to the ELBO. We demonstrate UIVI on several models, including Bayesian multinomial logistic regression and variational autoencoders, and show that UIVI achieves both tighter ELBO and better predictive performance than existing approaches at a similar computational cost.