A canal-lock keeper’s training curve either jumps wildly after each update or barely descends over many passes. What learning-rate idea best explains those two behaviors?
Select an answer to reveal the explanation.
Short Explanation
Step size is like how hard you turn the lock wheel: too hard and the water sloshes past the mark; too gentle and the level hardly changes. Large rates overshoot; tiny rates crawl. That is a conceptual learning-rate story, not a kernel rewrite.
Full Explanation
The learning rate scales how far parameters move on each update. Excessively large steps can cause unstable or diverging loss; excessively small steps can make training stall with little descent. Associate-level reasoning ties those curve shapes to step size, not to rewriting low-level GPU code.