No Free Lunch Theorem

The no free lunch Theorem is the belief that not one model that works best for every problem. This tells us that it is impossible to have a strategy that would apply to every problem. The only way that one strategy can be better than another is if the strategy is more related to the specific problem. Essentially it is a theory that debunks the idea that “My optimization X is the best” which normally applies in machine learning so it proves there is no one solution for everything.

Sources

http://www.cc.gatech.edu/~isbell/reading/papers/nfl-optimization-explanation.pdf

https://chemicalstatistician.wordpress.com/2014/01/24/machine-learning-lesson-of-the-day-the-no-free-lunch-theorem/

Advertisements

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s