https://en.wikipedia.org/wiki/Greek_letters_used_in_mathematics,_science,_and_engineering
Good wiki page. When reading AI/ML articles and papers, pseudocode and math is often written using greek symbols. Like Σ (sigma) for summing. Like, θ (theta) is for polar coordinates, or to refer to the ‘policy’ of an agent. STEM students osmose the many meanings of the symbols over years of study.
Was thinking about this, while looking at https://openai.com/blog/reptile/ and then rabbit-holed into the Adam optimiser and what it is. (It’s an SGD method : https://en.wikipedia.org/wiki/Stochastic_gradient_descent)
SGD algorithms can get super mathy.
When you learn Calculus, you first learn about differentiation, and Newton’s method, which is when you keep taking the derivative, and drawing a line. https://en.wikipedia.org/wiki/Newton’s_method
SGD is kinda like that but with a bit more statistics involved. Adam is using the second derivative too and keeping track of averages, etc., making it a bit more sophisticated than Newton’s method.
Finding where a derivative is zero, is how you find local optima and minima, and so SGD can lead you towards solutions. (Evolutionary algorithms offer a less direct path towards solutions, typically with a random variable element. For some problems, lower learning rates help avoid local optima traps (like the robot falling over face first, because of a reward for going forward).