Adversarial Learning of a Sampler Based on an Unnormalized Distribution

January 03, 2019 · Entered Twilight · 🏛 International Conference on Artificial Intelligence and Statistics

"Last commit was 7.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: .gitignore, README.md, constrained_sampling, entropy, figs, plots, sql

Authors Chunyuan Li, Ke Bai, Jianqiao Li, Guoyin Wang, Changyou Chen, Lawrence Carin arXiv ID 1901.00612 Category cs.LG: Machine Learning Cross-listed cs.AI, stat.ML Citations 10 Venue International Conference on Artificial Intelligence and Statistics Repository https://github.com/ChunyuanLI/RAS ⭐ 15 Last Checked 1 month ago

Abstract

We investigate adversarial learning in the case when only an unnormalized form of the density can be accessed, rather than samples. With insights so garnered, adversarial learning is extended to the case for which one has access to an unnormalized form u(x) of the target density function, but no samples. Further, new concepts in GAN regularization are developed, based on learning from samples or from u(x). The proposed method is compared to alternative approaches, with encouraging results demonstrated across a range of applications, including deep soft Q-learning.