•1 min read•from Towards Data Science
Reparameterization Tricks: Variance Reduction by Smarter Gradients
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.
Want to read more?
Check out the full article on the original site
Tagged with
#reparameterization tricks
#variance reduction
#gradients
#stochastic gradients
#computation graph
#randomness
#noisy estimators
#differentiable
#machine learning
#deep learning
#optimization
#neural networks
#estimator
#variance
#low-variance
#gradient estimators
#towards data science
#data science
#deep learning techniques
#gradient descent