Stochastic gradient descent (SGD) is a variant of gradient descent where only a small subset ("mini-batch") of training examples is used to compute the gradient on each iteration.

There is no tag wiki for this tag … yet!

Tag wikis help introduce newcomers to the tag. They contain an overview of the topic defined by the tag, along with guidelines on its usage.

All registered users may propose new tag wikis.

(Note that if you have less than 20000 reputation, your tag wiki will be peer reviewed before it is published.)

history | excerpt history