spectral-stein-grad

KO | EN

gitlite — search

#docker #react #golang #java #hacktoberfest #php #nodejs #minecraft #language #elixir #vim #chef

spectral-stein-grad

★ 34 Open GitHub ↗

Code for "A Spectral Approach to Gradient Estimation for Implicit Distributions" (ICML'18)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# spectral-stein-grad

**Update:** Please find our latest python library for nonparametric score estimation (including the spectral estimator) at
https://github.com/miskcoo/kscore

---

This repository contains the official code for

### A Spectral Approach to Gradient Estimation for Implicit Distributions (ICML 18)
https://arxiv.org/abs/1806.02925

## Dependencies
* [Tensorflow >= 1.8](https://www.tensorflow.org)
* [ZhuSuan >= 0.3.1](https://github.com/thu-ml/zhusuan)

## Get Started
```
python -m toy.guassian
```
<img src="results/gaussian.png" width="600">

### Implicit VAEs
Train plain VAE on CelebA:
```
python -m vae.vae_celeba
```
Train implicit VAE on CelebA using entropy gradients estimated by SSGE:
```
python -m vae.vae_celeba_implicit
```

## Citation
To cite this work, please use
```
@InProceedings{shi2018spectral,
  title = 	 {A Spectral Approach to Gradient Estimation for Implicit Distributions},
  author = 	 {Shi, Jiaxin and Sun, Shengyang and Zhu, Jun},
  booktitle = 	 {Proceedings of the 35th International Conference on Machine Learning},
  pages = 	 {4651--4660},
  year = 	 {2018},
}
```

spectral-stein-grad

Explore Similar Repositories

Was this content helpful?

Recent Feedback

Download README