Towards Data Science | Medium Follow Reparameterization Tricks: Variance Reduction by Smarter Gradients How moving randomness outside the computation graph turns noisy gradient estimators into low-variance, differentiable ones https://towardsdatascience.com/reparameterization-tricks-variance-reduction-by-smarter-gradients/ towardsdatascience.com AI and ML News on Bluesky @ai-news.at.thenote.app bsky.app
