ML EPS LOW: Difference between revisions

From VASP Wiki
No edit summary
No edit summary
Line 3: Line 3:
Description: Threshold for the CUR algorithm used in the sparsification of the machine learning force fields.  
Description: Threshold for the CUR algorithm used in the sparsification of 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 environments (for details see appendix E of reference {{cite|jinnouchi2:arx:2019}}). Small eigenvalues and those columns (local configurations) that are strongly connected
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 {{cite|jinnouchi2:arx:2019}}). 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. However, if extensive training is performed, we recommend to reduce the threshold to  
with these small eigenvalues are removed by the sparsification routines. The default value is fairly well balanced. However, if extensive training is performed, we recommend to reduce the threshold to  
1E-12. Unnecessary local environments can be removed in a post processing step (a single additional learning step with {{TAG|ML_FF_ISTART}}=1 using new parameters), after the on the fly learning
1E-12. Unnecessary local environments can be removed in a post processing step (a single additional learning step with {{TAG|ML_FF_ISTART}}=1 using new parameters), after the on the fly learning

Revision as of 08:34, 2 September 2020

ML_FF_EPS_LOW = [real]
Default: ML_FF_EPS_LOW = 1E-10 

Description: Threshold for the CUR algorithm used in the sparsification of 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. However, if extensive training is performed, we recommend to reduce the threshold to 1E-12. Unnecessary local environments can be removed in a post processing step (a single additional learning step with ML_FF_ISTART=1 using new parameters), after the on the fly learning has been finished.

Related Tags and Sections

ML_FF_LMLFF, ML_FF_MB_MB, ML_FF_LBASIS_DISCARD, ML_FF_LCONF_DISCARD

Examples that use this tag

References