mini-batch stochastic gradient descent

A gradient descent algorithm that uses mini-batches. In other words, mini-batch stochastic gradient descent estimates the gradient based on a small subset of the training data. Regular stochastic gradient descent uses a mini-batch of size 1.

Practitioners refer to mini-batch stochastic gradient descent when building, training, or evaluating machine learning systems. It appears in research papers, product documentation, and technical discussions about AI capabilities and limitations.