Corpus ID: 219558211

AR-DAE: Towards Unbiased Neural Entropy Gradient Estimation

@inproceedings{Lim2020ARDAETU,
  title={AR-DAE: Towards Unbiased Neural Entropy Gradient Estimation},
  author={Jae Hyun Lim and Aaron C. Courville and C. Pal and Chin-Wei Huang},
  booktitle={ICML},
  year={2020}
}
Entropy is ubiquitous in machine learning, but it is in general intractable to compute the entropy of the distribution of an arbitrary continuous random variable. In this paper, we propose the amortized residual denoising autoencoder (AR-DAE) to approximate the gradient of the log density function, which can be used to estimate the gradient of entropy. Amortization allows us to significantly reduce the error of the gradient approximator by approaching asymptotic optimality of a regular DAE, in… Expand

References

SHOWING 1-10 OF 58 REFERENCES
Deep Energy Estimator Networks
Auto-Encoding Variational Bayes
Generative Modeling by Estimating Gradients of the Data Distribution
Improving Variational Autoencoders with Inverse Autoregressive Flow
A Spectral Approach to Gradient Estimation for Implicit Distributions
Gradient Estimators for Implicit Models
Entropic GANs meet VAEs: A Statistical Approach to Compute Sample Likelihoods in GANs
Importance Weighted Autoencoders
A Connection Between Score Matching and Denoising Autoencoders
...
1
2
3
4
5
...