Pseudo-Random Number Generation
Explore how pseudo-random number generation works in JAX, focusing on stateless PRNGs like Threefry. Understand the advantages of JAX's approach including parallelization, smaller state vectors, and improved reproducibility for deep learning and numerical computing tasks.
Random variable
Consider a function:
No matter how many times we call this function, it will always give the same output for a given input.
On the other hand, consider some random/stochastic function; the seventh roll of the dice, the temperature at 3 PM, or the quantum state of a particle. All of them are never guaranteed to give the same output every time.
The outcome of this random function is known as a random variable. It’s hard to think of a field that doesn’t rely in some way on random variables. It’s no wonder that they play a central role in modeling almost any real-world system.
PRNG
One of the advantages computers ...