From cfa06418e1d500d1a6945bc37deffcddc7fa551f Mon Sep 17 00:00:00 2001 From: david-cortes Date: Sun, 25 Jun 2023 13:42:02 +0200 Subject: [PATCH] correct docs --- R/fit.R | 6 +++--- man/fit.Rd | 6 +++--- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/R/fit.R b/R/fit.R index 32ac912..c787ce0 100644 --- a/R/fit.R +++ b/R/fit.R @@ -492,7 +492,7 @@ NULL #' taking instead a fixed number of steps (given by `max_cg_steps`) at each iteration #' regardless of whether it has reached the optimum already. #' -#' Ignored when passing `use_cg=FALSE` or `method="als"`. +#' Ignored when passing `use_cg=FALSE` or `method="lbfgs"`. #' @param alpha Weighting parameter for the non-zero entries in the implicit-feedback #' model. See [3] for details. Note that, while the author's suggestion for #' this value is 40, other software such as the Python package `implicit` use a value of 1, @@ -769,8 +769,8 @@ NULL #' regularization to the \eqn{\mathbf{A}, \mathbf{B}}{A, B} matrices instead. #' #' For reproducibility, the initializations of the model matrices (always initialized -#' as `~ Normal(0, 1)`) can be controlled -#' through `set.seed`, but if using parallelizations, there are potential sources +#' as `~ Normal(0, 1)` for `CMF` and as `~ Uniform(0,1)` for `CMF_implicit`) can be controlled +#' through the seed parameter, but if using parallelizations, there are potential sources #' of irreproducibility of random seeds due to parallelized aggregations and/or #' BLAS function calls, which is especially problematic for the L-BFGS method #' with `parallelize='single'`. diff --git a/man/fit.Rd b/man/fit.Rd index 8f62699..cb7ceae 100644 --- a/man/fit.Rd +++ b/man/fit.Rd @@ -558,7 +558,7 @@ Note that, when using preconditioning, the procedure will not check for converge taking instead a fixed number of steps (given by `max_cg_steps`) at each iteration regardless of whether it has reached the optimum already. -Ignored when passing `use_cg=FALSE` or `method="als"`.} +Ignored when passing `use_cg=FALSE` or `method="lbfgs"`.} \item{finalize_chol}{When passing `use_cg=TRUE` and using the ALS method, whether to perform the last iteration with the Cholesky solver. This will make it slower, but will avoid the issue @@ -954,8 +954,8 @@ for new data will offer an option `exact` for determining whether to apply the regularization to the \eqn{\mathbf{A}, \mathbf{B}}{A, B} matrices instead. For reproducibility, the initializations of the model matrices (always initialized -as `~ Normal(0, 1)`) can be controlled -through `set.seed`, but if using parallelizations, there are potential sources +as `~ Normal(0, 1)` for `CMF` and as `~ Uniform(0,1)` for `CMF_implicit`) can be controlled +through the seed parameter, but if using parallelizations, there are potential sources of irreproducibility of random seeds due to parallelized aggregations and/or BLAS function calls, which is especially problematic for the L-BFGS method with `parallelize='single'`.