ML RDES SPARSDES: Difference between revisions

Latest revision as of 14:01, 20 March 2024

ML_RDES_SPARSDES = [real]
Default: ML_RDES_SPARSDES = 0.5

Description: Sets the ratio of descriptors kept during angular-descriptor sparsification.

Mind: This tag is only available as of VASP 6.4.3.

During angular-descriptor sparsification (ML_LSPARSDES=T), insignificant angular descriptors are removed based on a leverage scoring. The percentage of angular descriptors that are kept is determined by the value of ML_RDES_SPARSDES, which must be chosen between $0 < r \leq 1$ . In practice, we recommend scanning a range between 0.1 to 0.9. Removing angular descriptors increases the performance of a force field, but it decreases accuracy at the same time. One method of finding the optimal tradeoff between accuracy and performance is to do a Pareto front with run time on the x-axis and accuracy on the y-axis.

@@ Line 1: / Line 1: @@
-{{TAGDEF|ML_FF_RDES_SPARSDES_MB|[integer]|0.5}}
+{{DISPLAYTITLE:ML_RDES_SPARSDES}}
+{{TAGDEF|ML_RDES_SPARSDES|[real]|0.5}}
-Description: This tag sets ratio of the selected descriptors to the total number of descriptors within the sparsification of the angular descriptors is done within machine learning force fields.
+Description: Sets the ratio of descriptors kept during angular-descriptor sparsification.
+{{NB|mind|This tag is only available as of VASP 6.4.3.}}
 ----
-For details on the theory of angular descriptor sparsification see [[Machine learning force field: Theory#Sparsification of angular descriptors|here]].
-For details on how to use the sparsification see the tag {{TAG|ML_FF_LSPARSDES_MB}}.
+During [[Machine_learning_force_field:_Theory#Sparsification_of_angular_descriptors|angular-descriptor sparsification]] ({{TAG|ML_LSPARSDES}}=T), insignificant angular descriptors are removed based on a leverage scoring. The percentage of angular descriptors that are kept is determined by the value of {{TAG|ML_RDES_SPARSDES}}, which must be chosen between <math>0 < r \leq 1</math>. In practice, we recommend scanning a range between 0.1 to 0.9. Removing angular descriptors increases the performance of a force field, but it decreases accuracy at the same time. One method of finding the optimal tradeoff between accuracy and performance is to do a Pareto front with run time on the x-axis and accuracy on the y-axis.
-The values for {{TAG|ML_FF_RDES_SPARSDES_MB}} should be chosen between <math>0 \gt r \le 1</math>.
+== Related tags and articles ==
+{{TAG|ML_LMLFF}}, {{TAG|ML_LSPARSDES}}, {{TAG|ML_NRANK_SPARSDES}}, {{TAG|ML_DESC_TYPE}}
-== Related Tags and Sections ==
+{{sc|ML_EPS_LOW|Examples|Examples that use this tag}}
-{{TAG|ML_FF_LMLFF}}, {{TAG|ML_FF_LSPARSDES_MB}}, {{TAG|ML_FF_NRANK_SPARSDES_MB}}
-{{sc|ML_FF_EPS_LOW|Examples|Examples that use this tag}}
+[[Category:INCAR tag]][[Category:Machine-learned force fields]]
-[[Category:INCAR]][[Category:Machine Learning]][[Category:Machine Learned Force Fields]][[Category: Alpha]]