The principle of assigning to variables the probability distribution which has the maximum entropy given whatever information you have is one of those things that always just seemed right, and is why Gaussians appears everywhere in probability theory and practical estimation.
Quote Tweet
Many standard probability distributions can be obtained by solving a maximum-entropy optimization problem over distributions. For example, the Gaussian maximizes the entropy subject to mean and covariance constraints.
Jax source code: github.com/facebookresear
More resources: 
Show this thread
GIF
2
3
29
