If the gradient g is ill-conditioned, it will cost more time to train the model since in this situation the learning rate must shrink to cancel out the increase of gradient norm.

University of Minnesota - Twin Cities

Conditioning is used to describe the rate of change of a function as the input changes.
- The $\textbf{conditioning number}$ is used to describe how rapidly the function changes

Conditioning

Goodfellow, I., Bengio, Y., & Courville, A. (2016). $\mathit{Deep \ Learning.}$ MIT Press. Retrieved from [www.deeplearningbook.org](https://www.deeplearningbook.org) 

Learn Before

Related