Approximating the inverse of an expensive CDF function

There are lots of packages for polynomial interpolation in Julia that can be applied to approximate the inverses of expensive functions. See e.g. Approximate inverse of a definite integral - #3 by stevengj

I’m not sure if there is anything like this that is prepackaged to approximate inverse CDFs from data; presumably you want some kind of fit or spline if you have the numerical CDF (via the quantile function in the Statistics standard library, for example) evaluated on a grid. There are lots of packages in Julia for various forms of spline interpolation too, including monotonic Hermite splines — it should be straightforward to apply this to the quantile output, no?

PS. I split this post off into a new thread, rather than resurrecting a 3-year-old thread on a loosely related topic.

1 Like