The equation in question is $f(x) = x^4 - 4x - 2$ and I want to minimise the function. Regardless of whether it is ideal or not to use Newton-Raphson, which one would I use?
Sorry if this is a silly question, I'm new to ML and my math foundation is a little shaky.
As angryavian said in the comments, you have a univariate function, since your function consists only a single variable, which is $x$.
A multivariate function would be a function which consists more than one variables, such as $f(x,y) = x^2 - y^2 + xy$ for example.
Thus, you need to use the univariate version of N-R for your minimization problem.
By the way, from Wikipedia: "In mathematics, a univariate object is an expression, equation, function or polynomial involving only one variable. Objects involving more than one variable are multivariate."