Learn Before
Concept

Independent and Identically Distributed (IID) Assumption

In standard supervised learning, we commonly rely on the independent and identically distributed (IID) assumption. This principle dictates that both the training and test data are drawn independently from the exact same underlying probability distribution, denoted as P(X,Y)P(X,Y). Without this strong assumption that P()=Q()P(\cdot) = Q(\cdot) (where QQ is the test distribution), it would be impossible to justify using patterns learned from the training data to make predictions on new test data.

0

1

Updated 2026-05-03

Contributors are:

Who are from:

Tags

D2L

Dive into Deep Learning @ D2L

Learn After