SLIM
1.0
Sparse Linear Methods (SLIM) for top-n recommender systems
|
This file contains all the routines for SLIM learning with feature selection. More...
#include <slim.h>
Go to the source code of this file.
Functions | |
void | slim_fs_learn (ctrl_t *ctrl, gk_csr_t *A, double *b, double *w, float **A_colval, worksp *Wrk, double *bl, double *bu, double beta, double *c) |
SLIM learning with feature selction. | |
This file contains all the routines for SLIM learning with feature selection.
Definition in file slim_fs_learn.c.
void slim_fs_learn | ( | ctrl_t * | ctrl, |
gk_csr_t * | A, | ||
double * | b, | ||
double * | w, | ||
float ** | A_colval, | ||
worksp * | Wrk, | ||
double * | bl, | ||
double * | bu, | ||
double | beta, | ||
double * | c | ||
) |
SLIM learning with feature selction.
[in] | ctrl | A ctrl structure which contains all the parameters for SLIM Learning with feature selection |
[in] | A | The A matrix |
[in] | b | The RHS vector |
[in,out] | w | The solution vector |
[in] | A_colval | A temporary place for a column |
[in] | Wrk | A workspace for BCLS |
[in] | bl | The lower bound for BCLS |
[in] | bu | The upper bound for BCLS |
[in] | beta | The regularization parameter for L-2 norm |
[in] | c | The vector for L-1 norm |
Definition at line 31 of file slim_fs_learn.c.
References worksp::acol, bcsol(), count_nnz(), find_topk(), and ctrl_t::k.
Referenced by slim_learn().