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...
## Description The Drift Diffusion Model (DDM) introduced by Ratcliff provides a framework for analyzing data of fast binary decisions jointly modelling accuracy and response times. There are several parameterizations...
After FFT (#20) another complex-valued special function which would be good to have is Schur decomposition: https://en.wikipedia.org/wiki/Schur_decomposition This is probably a natural candidate to be the first function in the...
## Summary This is a very WIP PR, mostly for @charlesm93 and I to debug some things ## Tests ## Side Effects ## Release notes ## Checklist - [ ]...
## Description Several users have reported that `hmm_hidden_state` returns nan, in cases where the probability of the hidden state being in one particular state goes to 1. There seems to...
Cleaning up last few things before the release I tried to add poission_binomial to the language but C++ issue arose and should be cleaned up so we can finally expose...
Stan::Math exposes `value_type_t`, `base_type_t`, and `scalar_type_t`. Here is what the docs have to say about each: - value_type_t: Helper function for accessing underlying type. - base_type_t: [ (no documentation)](https://mc-stan.org/math/da/dce/namespacestan.html#ac0fcd9f3e82f72b645ce2eaf9d9a3eea) -...
*[edit: generalized for vectors by @bob-carpenter]* Add this signature for `to_matrix`: ```stan array[N_cols] vector[N_rows] arr_Vec ; matrix[N_rows,N_cols] mat_from_arr_Vec = to_matrix(arr_Vec) ;//proposed handling of new signature ``` and general signatures for...
## Description The method `stan::var::print_stack()` does currently only print the size of the stack. This was different in the past. It would be very handy to have more verbose information...
The following RNG functions are missing (where specific signatures are not listed, that means that no `_rng` signatures are implemented for that function): - [ ] bernoulli_logit_glm_rng ``` bernoulli_logit_glm_rng(matrix, real,...
## Description In order to fix the compile errors with multiplying/solving `CWiseUnaryViews` (which originally necessitated the `val_op` and `adj_op` member introductions), I've submitted patches to Eigen's code which are needed...
