Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Tutorial or example on embarrassingly parallel/consensus MCMC #417

Open
fehiepsi opened this issue Oct 28, 2019 · 2 comments · May be fixed by #277
Open

Tutorial or example on embarrassingly parallel/consensus MCMC #417

fehiepsi opened this issue Oct 28, 2019 · 2 comments · May be fixed by #277
Assignees
@fehiepsi
Labels
low priority Tutorials/Examples
Milestone
0.9

Comments

@fehiepsi
Copy link
Member

Despite that NumPyro is very fast (comparing to other frameworks), running MCMC for large datasets is still slow. Even that GPU helps us increase 10x the speed, it is still slow. This is when subposterior methods show their advantages. It is also a good chance to illustrate some available utilities consensus and parametric, which merge subposteriors together, to users.
@fehiepsi fehiepsi linked a pull request Jan 13, 2021 that will close this issue
Open
5 tasks
@fehiepsi fehiepsi added this to the 0.7 milestone May 12, 2021
@fehiepsi fehiepsi self-assigned this May 12, 2021
@fehiepsi fehiepsi modified the milestones: 0.7, 0.8 Jul 8, 2021
@fehiepsi fehiepsi modified the milestones: 0.8, 0.9 Dec 9, 2021
@EdwardRaff
Copy link

I have some upcoming work that I think this might solve, but the documentation is very sparse. Are the subposteriors the states from previous NUTS runs? Can it work with the DiscreteHMCGibbs sampler?

@fehiepsi
Copy link
Member Author

Yes, subposteriors come from NUTS runs with a shard of data. The method does not work with discrete ones I think.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@fehiepsi fehiepsi

Labels
low priority Tutorials/Examples
Projects
None yet
Milestone
0.9
Development

Successfully merging a pull request may close this issue.

Try flow hmc in covtype dataset fehiepsi/numpyro
2 participants
@EdwardRaff @fehiepsi