move change from V3.8 to V3.9

pymc-devs#3852 adds the new feature to the V3.8 changelog while it should go in the V3.9 changelog.

Author: tirthasheshpatel

RELEASE-NOTES.md

@@ -3,6 +3,7 @@
 ## PyMC3 3.9 (On deck)
 
 ### New features
+- A GP covariance functions can now be exponentiated by a scalar. See PR [#3852](https://github.com/pymc-devs/pymc3/pull/3852)
 - use [fastprogress](https://github.com/fastai/fastprogress) instead of tqdm [#3693](https://github.com/pymc-devs/pymc3/pull/3693)
 - `DEMetropolis` can now tune both `lambda` and `scaling` parameters, but by default neither of them are tuned. See [#3743](https://github.com/pymc-devs/pymc3/pull/3743) for more info.
 - `DEMetropolisZ`, an improved variant of `DEMetropolis` brings better parallelization and higher efficiency with fewer chains with a slower initial convergence. This implementation is experimental. See [#3784](https://github.com/pymc-devs/pymc3/pull/3784) for more info.
@@ -30,7 +31,6 @@
 - Distinguish between `Data` and `Deterministic` variables when graphing models with graphviz. PR [#3491](https://github.com/pymc-devs/pymc3/pull/3491).
 - Sequential Monte Carlo - Approximate Bayesian Computation step method is now available. The implementation is in an experimental stage and will be further improved.
 - Added `Matern12` covariance function for Gaussian processes. This is the Matern kernel with nu=1/2.
-- Added exponentiation of a covariance function with a scalar. See PR[#3852](https://github.com/pymc-devs/pymc3/pull/3852)
 - Progressbar reports number of divergences in real time, when available [#3547](https://github.com/pymc-devs/pymc3/pull/3547).
 - Sampling from variational approximation now allows for alternative trace backends [#3550].
 - Infix `@` operator now works with random variables and deterministics [#3619](https://github.com/pymc-devs/pymc3/pull/3619).