search

alashworth / test-issue-import

0 stars 0 forks source link

Enable optimization within .stan programs #60

Open alashworth opened 5 years ago

alashworth commented 5 years ago

Issue by bgoodri Saturday Feb 28, 2015 at 20:37 GMT Originally opened as https://github.com/stan-dev/stan/issues/1319

This would be similar to integrate_ode but instead of calling

theta <- integrate_ode(sho, ...);

it would be something like

theta <- solve_equations(system, ...); // calls Eigen::HybridNonLinearSolver

and / or

theta <- minimize(loss, ...); // calls LBFGS or something in Boost

We would have to make sure the derivatives due to the implicit function get put in the right place. There is a review paper that discusses such constructs in Bayesian models at http://onlinelibrary.wiley.com.ezproxy.cul.columbia.edu/doi/10.1002/9781118771051.ch11/pdf

alashworth commented 5 years ago

Comment by khakieconomics Tuesday Mar 07, 2017 at 18:33 GMT

Is this still a proposed feature? It would be quite useful for some work I am doing.

alashworth commented 5 years ago

Comment by rtrangucci Tuesday Mar 07, 2017 at 19:14 GMT

Ben, I can't access the paper you posted, do you have the author/title info?

Rob

On Tue, Mar 7, 2017 at 1:33 PM, Jim notifications@github.com wrote:

Is this still a proposed feature? It would be quite useful for some work I am doing.

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/stan-dev/stan/issues/1319#issuecomment-284813647, or mute the thread https://github.com/notifications/unsubscribe-auth/ADvmhxKMTVeKEPEA1CSb7UVFY9Y9yIMFks5rjaLegaJpZM4DngLV .

alashworth commented 5 years ago

Comment by jgabry Tuesday Mar 07, 2017 at 19:20 GMT

It's a chapter called "Approximate Bayesian Inference in Models Defined Through Estimating Equations" from the book Bayesian Inference in the Social Sciences. DOI: 10.1002/9781118771051.ch11

On Tue, Mar 7, 2017 at 2:14 PM, Rob Trangucci notifications@github.com wrote:

Ben, I can't access the paper you posted, do you have the author/title info?

Rob

On Tue, Mar 7, 2017 at 1:33 PM, Jim notifications@github.com wrote:

Is this still a proposed feature? It would be quite useful for some work I am doing.

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/stan-dev/stan/issues/1319#issuecomment-284813647, or mute the thread https://github.com/notifications/unsubscribe-auth/ ADvmhxKMTVeKEPEA1CSb7UVFY9Y9yIMFks5rjaLegaJpZM4DngLV

.

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/stan-dev/stan/issues/1319#issuecomment-284825377, or mute the thread https://github.com/notifications/unsubscribe-auth/AHb4Q4-dHctxXxHakKOuFRm94qCS65M8ks5rjayFgaJpZM4DngLV .