... | ... | @@ -23,17 +23,9 @@ The results can be seen below. The displayed errorbars are taken to be standard |
|
|
### Empirical evidence uncertainties vs. K-L-divergence uncertainties
|
|
|
|
|
|
The sampling packages quote evidence uncertainties by calculating a K-L divergence. We want to test whether this quoted uncertainty is truly Gaussian, i.e. is the true evidence covered by the 1(2)-sigma interval ~68(95)% of the time, etc.
|
|
|
We can display these results most conveniently by creating percentile-percentile style plots. Specifically, we look at the results of dynesty and Polychord as a reference.
|
|
|
We can display these results most conveniently by creating percentile-percentile style plots. Specifically, we look at the results of dynesty and Polychord.
|
|
|
|
|
|
|
|
|
|
|
|
Review items:
|
|
|
|
|
|
* run analytical likelihoods multiple times for a range of live points (32, 64, 128, 256, 512, 1024, 2048, 4096). Compare empirical uncertainties on log evidence values from the multiple runs to the uncertainty calculated using the K-L divergence (information gain).
|
|
|
* Here is a preliminary plot for this test. The mean log evidence is averaged over 100 runs. The error bars are calculated using the standard deviation on the log evidences.
|
|
|
|
|
|
![summary_unimodal_no_covariance](uploads/debed7905047abe60e6fe5e4a14e2b84/summary_unimodal_no_covariance.png)
|
|
|
|
|
|
## LALInference comparison
|
|
|
|
|
|
Compare the evidence produced by the standard bilby run on GW150914 with the LALInference evidence. Run for individual detectors and a coherent multi-detector analysis.
|
... | ... | |