Gradient descent can get stuck into local optimum. Which techniques are there to reach global optimum?

| improve this question | | | | |

In Deep Learning there are several methods to improve "stuck" gradient - decrease learning rate, use cyclic learning rate - cycle it from bigger to smaller value. More radical method is completely reinitialize last or two last (before loss) layers of the network.

In non-Deep Learning ML out of those only decrease learning rate will work, but there is plethora Numerical Optimization methods to help, like second-order methods - variation of Gauss-Newton, or methods specific to the problem which may include projective methods, alternate directions, conjugate gradients etc. There are a lot of methods which are better then gradient descent for non-Deep Learning optimization.

| improve this answer | | | | |

Your Answer

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

Not the answer you're looking for? Browse other questions tagged or ask your own question.