No Free Lunch Theorem
Statement (s.364): there is no one algorithm that is always the most accurate.
Consequences given on the slide:
- Focus on obtaining base models that make different kinds of errors, rather than highly accurate base models (diversity for ensembles).
- Build weak learners that are at least more accurate than random guessing.
- Keep trying (experimenting, tuning, etc.).
Related
Concept - Netflix Prize | Concept - Sentiment Analysis