Data Science Wire

Reparameterization Tricks: Variance Reduction by Smarter Gradients

Towards Data Science10h4 min read

How moving randomness outside the computation graph turns noisy gradient estimators into low-variance, differentiable ones The post Reparameterization Tricks: Variance Reduction by Smarter Gradients appeared first on Towards Data Science .

Read the full story at Towards Data Science

More in Machine Learning