<p>How moving randomness outside the computation graph turns noisy gradient estimators into low-variance, differentiable ones</p>
<p>The post <a href="https://towardsdatascience.com/reparameterization-tricks-variance-reduction-by-smarter-gradients/">Reparameterization Tricks: Variance Reduction by Smarter Gradients</a> appeared first on <a href="https://towardsdatascience.com">Towards Data Science</a>.</p>