The concrete distribution: A continuous relaxation of discrete random variables
The reparameterization trick enables optimizing large scale stochastic computation graphs via gradient descent. The essence of the trick is to refactor each stochastic node into a differentiable function of its parameters and a random variable with fixed distribution. After refactoring, the gradient...
| Main Authors: | , , |
|---|---|
| 格式: | Conference item |
| 出版: |
International Conference on Learning Representations
2017
|