What does log-uniformly distribution mean?

When someone say a data is sampled from a log-uniformly distribution between 128 and 4000, what does that mean? How that different to sampling from a uniformly distribution?

See this paper: http://www.jmlr.org/papers/volume13/bergstra12a/bergstra12a.pdf

Thanks!

Answer

I believe it means that the log is uniformly distributed, and the variable takes values in the range $[128, 4000]$.

From a footnote of the paper:

We will use the phrase drawn geometrically from A to B for 0 < A < B to mean drawing uniformly in the log domain between log(A) and log(B), exponentiating to get a number between A and B, and then rounding to the nearest integer. The phrase drawn exponentially means the same thing but without rounding.

Like this:

x <- exp(runif(100000, log(128), log(4000)))
hist(x, breaks=100, xlim=c(128, 4000))

enter image description here

hist(log(x), breaks=100, xlim=c(log(128), log(4000)))

enter image description here

Attribution
Source : Link , Question Author : RockTheStar , Answer Author : Matthew Drury

Leave a Comment