What Will Happen If the Learning Rate Is Set inaccurately (Too Low or Too High)?

What Will Happen If the Learning Rate Is Set inaccurately (Too Low or Too High)?

A too high learning rate will make the learning jump over minima but a too low learning rate will either take too long to converge or get stuck in an undesirable local minimum.

Learning rate is very well explained in google’s open source platform
Check this out, you will appreciate the beauty
https://developers.google.com/machine-learning/crash-course/fitter/graph