# Hierarchical Implicit Models and Likelihood-Free Variational Inference

arXiv: https://arxiv.org/abs/1702.08896 · HTML: https://mlsanity.com/paper/1702.08896/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Feb 2017.

## Built on by (most cited first, 13 of 13)

- [Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis](https://mlsanity.com/paper/2101.04775/) (2021)
- [DG-Font: Deformable Generative Networks for Unsupervised Font Generation](https://mlsanity.com/paper/2104.03064/) (2021)
- [Can Push-forward Generative Models Fit Multimodal Distributions?](https://mlsanity.com/paper/2206.14476/) (2022)
- [DRANet: Disentangling Representation and Adaptation Networks for Unsupervised Cross-Domain Adaptation](https://mlsanity.com/paper/2103.13447/) (2021)
- [Is MC Dropout Bayesian?](https://mlsanity.com/paper/2110.04286/) (2021)
- [SurfGen: Adversarial 3D Shape Synthesis with Explicit Surface Discriminators](https://mlsanity.com/paper/2201.00112/) (2022)
- [Self-Supervised GANs with Label Augmentation](https://mlsanity.com/paper/2106.08601/) (2021)
- [GaussiGAN: Controllable Image Synthesis with 3D Gaussians from Unposed Silhouettes](https://mlsanity.com/paper/2106.13215/) (2021)
- [Multi-Stage Raw Video Denoising with Adversarial Loss and Gradient Mask](https://mlsanity.com/paper/2103.02861/) (2021)
- [DGFont++: Robust Deformable Generative Networks for Unsupervised Font Generation](https://mlsanity.com/paper/2212.14742/) (2022)
- [An Empirical Study on GANs with Margin Cosine Loss and Relativistic Discriminator](https://mlsanity.com/paper/2110.11293/) (2021)
- [Learning Individual Interactions from Population Dynamics with Discrete-Event Simulation Model](https://mlsanity.com/paper/2205.02332/) (2022)
- [Learning variational autoencoders via MCMC speed measures](https://mlsanity.com/paper/2308.13731/) (2023)

## Abstract (arXiv)

Implicit probabilistic models are a flexible class of models defined by a simulation process for data. They form the basis for theories which encompass our understanding of the physical world. Despite this fundamental nature, the use of implicit models remains limited due to challenges in specifying complex latent structure in them, and in performing inferences in such models with large data sets. In this paper, we first introduce hierarchical implicit models (HIMs). HIMs combine the idea of implicit densities with hierarchical Bayesian modeling, thereby defining models via simulators of data with rich hidden structure. Next, we develop likelihood-free variational inference (LFVI), a scalable variational inference algorithm for HIMs. Key to LFVI is specifying a variational family that is also implicit. This matches the model's flexibility and allows for accurate approximation of the posterior. We demonstrate diverse applications: a large-scale physical simulator for predator-prey populations in ecology; a Bayesian generative adversarial network for discrete data; and a deep implicit model for text generation.