AI engineering glossary · ML fundamentals
What is no free lunch theorem?
No free lunch theorem (also called NFL theorem): A theoretical result stating that, averaged over all possible problems, no learning algorithm is better than any other. It means an algorithm is only good to the extent its assumptions match the problem at hand, so practitioners must test several approaches on their own data.
No free lunch theorem: an example
A method that excels on image data can perform worse than a simple rule on some tabular data; neither is best everywhere.
Related terms
More ML fundamentals terms
- Noise
- Non-parametric model
- Occam's razor
- Online learning
- Out-of-distribution
- Outlier
- Overfitting
- Overparameterisation
Where you learn it
No free lunch theorem is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.