Closed matt-graham closed 6 months ago
Here is some fruther feedback from my side, also in the context of the JOSS review https://github.com/openjournals/joss-reviews/issues/6372
p. 1 L 20 "To accelerate and smooth this process" (and L36 "smoothed accelerated sampling problem")
p. 1 L 36 (listing the sampling methods)
p. 2 L53 "order of 10^2 evaluations of the code"
p. 2 L61 "ensemble Methods"
p. 2 L68 "the goal ABC is"
p. 2 L65 and L72 "GpABC" vs "gpABC"
p. 2 L72 "ABC can be used in more general contexts than CES, but suffers greater approximation error and more stringent assumptions, especially in multi-dimensional problems."
Figure 1
[x] Rather a cosmetic problem: the legend says true amplitude = 6.99, but the text in the paper says 7.0 (seems to be an artifact from the signal being made up of finite amount of samples, examples/Sinusoid/sinusoid_setup.jl:61
).
Ok, the legend is the mean, the text is the vertical shift, so perhaps one could consider it a property of the model (or finite number of "measurements"), but it is a bit confusing.
[x] I think it would make more sense if the observed range (blue double arrow) would be centered with respect to the observed mean (blue dashed line). But your version can be compared to the true values more easily, so feel free to ignore.
Figure 4, caption: "... trained on the re-used calibration pairs"
p. 5 L104 "histogram of the samples from (...?) is displayed in Figure 5."
Hi both - thanks for these comments. I shall create a PR shortly for to begin addressing them in the markdown. I have added check-boxes to the comments to aid in tracking them.
@nluetts as a couple of responses to your questions.
I believe we have addressed everything, Please close the issue if you are satisfied.
@odunbar thanks for clarifying, and thanks for the pointer to "Barker proposal", which I did not know about so far.
In this new sentence:
Two such examples, written in python, approximate the log-posterior distribution ...
you could capitalize Python.
@matt-graham the issue can be closed from my side :+1:
Thanks @odunbar - this looks all good to me too.
Raising issue as part of openjournals/joss-reviews/issues/6372
Some minor comments / suggestions for improvement of JOSS paper