Adversarial Learning of a Sampler Based on an Unnormalized Distribution
By Chunyuan Li, Ke Bai, Jianqiao Li, Guoyin Wang, Changyou Chen, Lawrence Carin. 2019
10 citations recorded by the source corpus.
Fundamental aspects of adversarial learning are investigated, with learning based on samples from the target distribution (conventional GAN setup). 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.
Subfields: Artificial Intelligence, Biophysics, Media Technology
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
In Biophysics
In Media Technology
Citations in the corpus
- Batch Stationary Distribution Estimation (2020, background): “Recent advances have also shown that learning parametric samplers can be beneficial (Song et al., 2017; Li et al., 2019), but require the potential function.”
- GenDICE: Generalized Offline Estimation of Stationary Values (2020, background): “Amortized SVGD (Wang & Liu, 2016) and Adversarial MCMC (Song et al., 2017; Li et al., 2019) alleviate this issue via combining with neural network, but they still interact with the transition operator directly, i.e., in an on-policy setting.”
- On Fenchel Mini-Max Learning (2019, methodology): “[38] adversarially updates the sampler based on the adaptive contrast technique [47].”
- Feature Quantization Improves GAN Training (2020, background): “, 2017) and sampling from unnormalized distributions (Li et al., 2019).”