ML EPS LOW: Difference between revisions
No edit summary |
No edit summary |
||
| Line 7: | Line 7: | ||
below 1E-9. Using smaller values than 1E-9, does not improve the MLFF if Bayesian regression is used. | below 1E-9. Using smaller values than 1E-9, does not improve the MLFF if Bayesian regression is used. | ||
The description how to choose {{TAG|ML_EPS_LOW}} for accurate force fields | The description how to choose {{TAG|ML_EPS_LOW}} for accurate force fields is given [[Machine learning force field calculations: Basics#Accurate force fields|here]]. | ||
On the theory of the sparsification of local reference configurations see | On the theory of the sparsification of local reference configurations see | ||
Revision as of 13:03, 16 February 2022
ML_EPS_LOW = [real]
Default: ML_EPS_LOW = 1E-9 (vasp.6.3.1 default was 1E-10, see comments below)
Description: Threshold for the CUR algorithm used in the sparsification of local reference configurations within the machine learning force fields.
This value sets the threshold for the eigenvalues that contribute to the leverage scoring used in the CUR algorithm for the rank compression ("sparsification") of the local configurations (for details see appendix E of reference [1]). Small eigenvalues and those columns (local configurations) that are strongly connected with these small eigenvalues are removed by the sparsification routines. The default value is fairly well balanced, and we do not recommend to reduce the threshold to values below 1E-9. Using smaller values than 1E-9, does not improve the MLFF if Bayesian regression is used.
The description how to choose ML_EPS_LOW for accurate force fields is given here.
On the theory of the sparsification of local reference configurations see here.
Related Tags and Sections
ML_LMLFF, ML_MB, ML_EPS_REG, ML_IALGO_LINREG
References