I don't know much about stochastic mirror descent and was wondering if someone could briefly summarize it in general terms and compare/contrast it to stochastic gradient descent.

When I understand correctly, mirror descent is an optimization algorithm for discrete optimization (in contrast to gradient descent), and the term stochastic comes from the fact that we, similar to stochastic gradient descent, approximate the training set loss to be minimized based on subsets of the training set (aka, 1 randomly and independently example at a time for true stochastic gradient descent and subsets for minibatch learning)?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.