Optimization · Level 2 of 5
Optimization
Choosing variable values to improve an objective subject to constraints.
Numerical optimization can converge imperfectly or stop at a non-global solution.
Example
A training procedure seeks parameters with lower loss.
Listen to the definition and example
Audio transcript
Optimization. Choosing variable values to improve an objective subject to constraints. Numerical optimization can converge imperfectly or stop at a non-global solution. For example: A training procedure seeks parameters with lower loss.
Explore this concept
Why it matters
This helps you understand what parameter updates are trying to improve and when they can fail.
Start with
Related concepts
Quick recall question
Try answering before looking back at the definition.