There's more...

To understand what is happening, we should look at how a large learning rate and small learning rate act on L1 norms and L2 norms. To visualize this, we look at a one-dimensional representation of learning steps on both norms, as follows:

Figure 7: What can happen with the L1 and L2 norm with larger and smaller learning rates

Get TensorFlow Machine Learning Cookbook - Second Edition now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.