search

bilby-dev / bilby

A unified framework for stochastic sampling packages and gravitational-wave inference in Python.
https://bilby-dev.github.io/bilby/
MIT License
59 stars 71 forks source link

hyper-parameter estimation likelihood #127

Closed bilby-bot closed 1 month ago

bilby-bot commented 6 years ago

In GitLab by @git.ligo:eric.thrane on May 16, 2018, 01:47

Several people (@git.ligo:colm.talbot, @git.ligo:gregory.ashton, @grant.meadors) have urgent need to do hyper-parameter estimation with tupak. There are multiple applications, but we should create a single function that can be adapted to all of these applications.

I recommend that we create a python function to do this. The inputs should include

@git.ligo:sylvia.biscoveanu

bilby-bot commented 6 years ago

In GitLab by @git.ligo:gregory.ashton on May 16, 2018, 01:55

mentioned in commit 261e9567c1ae5fd5470f12113ae12e47c3f5d763

bilby-bot commented 6 years ago

In GitLab by @git.ligo:gregory.ashton on May 16, 2018, 01:57

I've adding a MR (!41) with the basic version that I've got so far. Feel free to either just copy it, or pull the branch and edit and push. It is missing lots of the full functionality required. Currently it will only work with a single hyperparameter and just takes functions for the hyper prior and run prior.

bilby-bot commented 6 years ago

In GitLab by @git.ligo:gregory.ashton on May 22, 2018, 07:31

We now have a a hyperparameter likelihood and example, merged in commit 1d4772b1. You can run this example to see how it works.

Currently, its only implemented for a single hyperparameter inference. I'll leave this issue open to remind us that that should be fixed.

bilby-bot commented 6 years ago

In GitLab by @git.ligo:eric.thrane on May 22, 2018, 08:24

Nice, @git.ligo:gregory.ashton. Does this mean that your particular hyper-PE demo is working?

bilby-bot commented 6 years ago

In GitLab by @git.ligo:gregory.ashton on May 22, 2018, 11:59

Yes, the example script works as expected :)

bilby-bot commented 6 years ago

In GitLab by @git.ligo:gregory.ashton on Jun 19, 2018, 11:47

marked the checklist item Create general tupak.hyper-pe function. as completed

bilby-bot commented 6 years ago

In GitLab by @git.ligo:gregory.ashton on Jun 19, 2018, 11:47

bilby-bot commented 6 years ago

In GitLab by @git.ligo:colm.talbot on Jun 28, 2018, 00:28

See https://git.ligo.org/Monash/tupak/merge_requests/93, this generalises and speeds up the existing hyper pe likelihood.

bilby-bot commented 6 years ago

In GitLab by @git.ligo:colm.talbot on Jul 6, 2018, 06:33

closed

bilby-bot commented 1 month ago

In GitLab by @git.ligo:michael.williams on Oct 3, 2024, 17:56

unassigned @git.ligo:gregory.ashton