ML ICRITERIA: Difference between revisions

From VASP Wiki
VisualWikitext
No edit summary
No edit summary
Line 3: Line 3:
Description: Decides whether ({{TAG|ML_ICRITERIA}}>0) or how the Bayesian error threshold ({{TAG|ML_CTIFOR}}) is updated within the machine learning force field method. {{TAG|ML_CTIFOR}} determines whether a first principles calculations is performed.
Description: Decides whether ({{TAG|ML_ICRITERIA}}>0) or how the Bayesian error threshold ({{TAG|ML_CTIFOR}}) is updated within the machine learning force field method. {{TAG|ML_CTIFOR}} determines whether a first principles calculations is performed.
----
----
The usage of this tag in combination with the learning algorithms is described here: [[Machine learning force field calculations: Important algorithms#Threshold for error of forces|here]].
The following options are possible for {{TAG|ML_ICRITERIA}}:
The following options are possible for {{TAG|ML_ICRITERIA}}:
* {{TAG|ML_ICRITERIA}} = 0: No update of the threshold {{TAG|ML_CTIFOR}} is done.
* {{TAG|ML_ICRITERIA}} = 0: No update of the threshold {{TAG|ML_CTIFOR}} is done.
Line 8: Line 10:
* {{TAG|ML_ICRITERIA}} = 2: Update of criteria using gliding average of Bayesian errors (probably more robust but '''not well tested''').  
* {{TAG|ML_ICRITERIA}} = 2: Update of criteria using gliding average of Bayesian errors (probably more robust but '''not well tested''').  


Generally it is recommended to automatically update the threshold {{TAG|ML_CTIFOR}} during machine learning. Details on how and when the update is performed are controlled by {{TAG|ML_CSLOPE}}, {{TAG|ML_CSIG}} and {{TAG|ML_MHIS}}.
Description of {{TAG|ML_ICRITERIA}}=1:
{{TAG|ML_CTIFOR}} is generally 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_MHIS}}. To avoid that noisy data or an abrupt jump of the Bayesian error causes issues, the standard error of the history must be below the threshold  {{TAG|ML_CSIG}}, for the update to take place. Furthermore, the slope of the stored data must be below the threshold  {{TAG|ML_CSLOPE}} (we recommend to set only {{TAG|ML_CSIG}}).
If the previous conditions are met, the threshold {{TAG|ML_CTIFOR}} is updated. To avoid too abrupt changes the average Bayesian error can be mixed with the current value of  {{TAG|ML_CTIFOR}}. The mixing ratio can be determined by the tag {{TAG|ML_CX}} (default is no mixing).


== Related Tags and Sections ==
== Related Tags and Sections ==
{{TAG|ML_LMLFF}}, {{TAG|ML_CTIFOR}}, {{TAG|ML_CSLOPE}}, {{TAG|ML_CSIG}}, {{TAG|ML_MHIS}}, {{TAG|ML_XMIX}}
{{TAG|ML_LMLFF}}, {{TAG|ML_CTIFOR}}, {{TAG|ML_CSLOPE}}, {{TAG|ML_CSIG}}, {{TAG|ML_MHIS}}, {{TAG|ML_XMIX}}


{{sc|ML_ICRITERIA|Examples|Examples that use this tag}}
{{sc|ML_ICRITERIA|Examples|Examples that use this tag}}

Revision as of 17:24, 21 October 2021

ML_ICRITERIA = [integer]
Default: ML_ICRITERIA = 1 

Description: Decides whether (ML_ICRITERIA>0) or how the Bayesian error threshold (ML_CTIFOR) is updated within the machine learning force field method. ML_CTIFOR determines whether a first principles calculations is performed.

The usage of this tag in combination with the learning algorithms is described here: here.

The following options are possible for ML_ICRITERIA:

  • ML_ICRITERIA = 0: No update of the threshold ML_CTIFOR is done.
  • ML_ICRITERIA = 1: Update of criteria using average of the Bayesian errors of the forces from history (see description of method below).
  • ML_ICRITERIA = 2: Update of criteria using gliding average of Bayesian errors (probably more robust but not well tested).


Related Tags and Sections

ML_LMLFF, ML_CTIFOR, ML_CSLOPE, ML_CSIG, ML_MHIS, ML_XMIX

Examples that use this tag

Retrieved from "https://www.vasp.at/wiki/index.php?title=ML_ICRITERIA&oldid=13106"