Ever wondered how scientists know if two things are the same or not?
Kolmogorov–Smirnov test
Ever wondered how scientists know if two things are the same or not?
Imagine you're tasting two different brands of chocolate, and you want to know if they're equally delicious.
Think of the Kolmogorov-Smirnov test as a way to measure how much the taste of chocolate from one brand differs from the other, by comparing the smoothness of their taste curves.
Example
If one chocolate's taste curve rises slowly and the other's rises quickly, the test picks up this difference.
Remember this
The Kolmogorov-Smirnov test helps us see if there's a noticeable difference in taste curves between two chocolates.
Text adapted from Wikipedia, licensed under CC BY-SA 4.0.
Related concepts
Hellinger distance
Ever wondered how to measure differences between two things?
Likelihood function
Why can't we just guess probabilities correctly all the time?
Entropy H = -Σ p(x) log₂ p(x) measures average surprise in bits
How do we measure uncertainty in everyday decisions?
Bayesian inference
Ever wondered how doctors update diagnoses as new symptoms arise?
Top-k vs top-p sampling: top-k fixes candidate count, top-p fixes cumulative probability mass
Top-k sampling fixes candidate count; top-p sampling fixes cumulative probability mass
KL divergence is always ≥ 0 and equals 0 only when P = Q exactly
Why can't we just compare two things directly?
Swipe through more Machine Learning concepts
Open Pocket Polymath