AI engineering glossary · Deep learning core

What is cyclical learning rate?

Cyclical learning rate (also called Triangular schedule): A policy that swings the learning rate between a lower and an upper bound repeatedly instead of only decreasing it. It can reduce tuning effort and help training cross flat regions or saddle points.

Level: advancedTopic: Deep learning core

Cyclical learning rate: an example

The rate might rise from 0.001 to 0.01 and back over every 2,000 iterations.

Related terms

More Deep learning core terms

Where you learn it

Cyclical learning rate is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.

Before you go

Take the cheat sheet with you

One free PDF: the key AI-engineering terms, formulas and Python idioms. No spam; unsubscribe any time.