math
math copied to clipboard
stan-dev
The Stan Math Library is a C++ template library for automatic differentiation of any order using forward, reverse, and mixed modes. It includes a range of built-in functions for probabilistic modelin...
The ldlt code can basically piggy back off of the the reverse mode cholesky adjoints. In the cholesky reverse mode code it already handles the diagonal and off diagonal elements...
#### Summary: The mpi_cluster resource in stan-math should be revisited and it's design possibly improved. #### Description: The suggested improvements which need consideration are - better doc for `listening_state` method...
#### Summary: The MPI makefiles currently do not build boost in parallel and they also do not integrate well with cmdstan. #### Description: * Builds are slow due to not...
#### Summary: The mpi_cluster requires instantiated objects. Currently, this code is not handled in an aligned way in comparison to the stan repo. This should be aligned. #### Description: Some...
## Description The MPI build currently has problems whenever older boost version are on a given system as the wrong boost serialization is linked in. ## Example For **bug reports**:...
#### Summary: Now we malloc and check for alignment. C++11 provides an `alignas` mechanism where we can guarantee alignment on `double`. #### Current Version: v2.15.0
## Summary This shows that `multi_normal` should just take the cholesky decomposition and call `multi_normal_cholesky`. I just copied all the `multi_normal_cholesky_lpdf` code over. I wasn't sure how to just call...
## Description Print and reject should both properly handle the printing of tuples. A call `stan::math::print(std::tuple{1, 2.5})` should result in printing `(1, 2.5)`
## Description Describe the issue as clearly as possible. Issues are meant for bug reports and feature requests. The issue should contain enough information for a developer to put together...
## Description As I want to add a function with 8 known partials to the stan-math library (#2682), I had to extend the `operands_and_partials` routine such that it can work...
