ML ICRITERIA: Difference between revisions

From VASP Wiki
(Added more extensive description)
(Further updates reference ML_FF_SLOPE added)
Line 6: Line 6:
This flag is only used if Bayesian error estimation is switched on ({{TAG|ML_FF_IERR}}=2 or 3). Generally it is recommended to automatically update the criteria {{TAG|ML_FF_CTIFOR}} during machine learning. Details on whether the update is performed are controlled by {{TAG|ML_FF_CSLOPE}}, {{TAG|ML_FF_CSIG}} and {{TAG|ML_FF_MHIS}}.
This flag is only used if Bayesian error estimation is switched on ({{TAG|ML_FF_IERR}}=2 or 3). Generally it is recommended to automatically update the criteria {{TAG|ML_FF_CTIFOR}} during machine learning. Details on whether the update is performed are controlled by {{TAG|ML_FF_CSLOPE}}, {{TAG|ML_FF_CSIG}} and {{TAG|ML_FF_MHIS}}.


{{TAG|ML_FF_CTIFOR}} is set to the average of the  Bayesian errors of the forces stored in the history. The number of entries in the history are controlled by  {{TAG|ML_FF_MHIS}}. To avoid that noise data or an abrupt jump in the Bayesian error causes issues, the standard error of the history most be below the threshold  {{TAG|ML_FF_CSIG}}.
{{TAG|ML_FF_CTIFOR}} is set to the average of the  Bayesian errors of the forces stored in a history. The number of entries in the history are controlled by  {{TAG|ML_FF_MHIS}}. To avoid that noisy data or an abrupt jump of the Bayesian error causes issues, the standard error of the history most be below the threshold  {{TAG|ML_FF_CSIG}}, for the update to take place. Furthermore, the slope of the stored data must be below the threshold  {{TAG|ML_FF_CSLOPE}} (we recommend to set only  {{TAG|ML_FF_CSIG}}).


== Related Tags and Sections ==
== Related Tags and Sections ==

Revision as of 07:15, 16 April 2021

ML_FF_LCRITERIA = [logical]
Default: ML_FF_LCRITERIA = .TRUE. 

Description: Decides whether the threshold (ML_FF_CTIFOR) is updated in the machine learning force field methods.


This flag is only used if Bayesian error estimation is switched on (ML_FF_IERR=2 or 3). Generally it is recommended to automatically update the criteria ML_FF_CTIFOR during machine learning. Details on whether the update is performed are controlled by ML_FF_CSLOPE, ML_FF_CSIG and ML_FF_MHIS.

ML_FF_CTIFOR is set to the average of the Bayesian errors of the forces stored in a history. The number of entries in the history are controlled by ML_FF_MHIS. To avoid that noisy data or an abrupt jump of the Bayesian error causes issues, the standard error of the history most be below the threshold ML_FF_CSIG, for the update to take place. Furthermore, the slope of the stored data must be below the threshold ML_FF_CSLOPE (we recommend to set only ML_FF_CSIG).

Related Tags and Sections

ML_FF_LMLFF, ML_FF_IERR, ML_FF_CTIFOR, ML_FF_ISAMPLE, ML_FF_CSLOPE, ML_FF_CSIG, ML_FF_MHIS

Examples that use this tag