ML EPS LOW: Difference between revisions

Latest revision as of 11:42, 15 May 2023

Default: ML_EPS_LOW	= 1E-11	for ML_MODE = SELECT, REFIT
	= 1E-9	else (vasp.6.3.0 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 increase the threshold to values larger than 1E-7. Also using smaller values than 1E-9 does not improve the MLFF if Bayesian regression is used (but it can be benficial for SVD).

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.

References

↑ R. Jinnouchi, F. Karsai, and G. Kresse, Phys. Rev. B 100, 014105 (2019).

[jinnouchi2:arx:2019-1] R. Jinnouchi, F. Karsai, and G. Kresse, Phys. Rev. B 100, 014105 (2019).

[1]

@@ Line 1: / Line 1: @@
-{{TAGDEF|ML_FF_EPS_LOW|[real]|1E-10}}
+{{DISPLAYTITLE:ML_EPS_LOW}}
+{{TAGDEF|ML_EPS_LOW|[real]}}
+{{DEF|ML_EPS_LOW|1E-11|for {{TAG|ML_MODE}} {{=}} SELECT, REFIT|1E-9|else (vasp.6.3.0 default was 1E-10, see comments below)}}
-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 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 sparsification within the machine learning force fields (for details see appendix of reference {{cite|jinnouchi2:arx:2019}}). Only eigenvalues that are larger than this threshold lead to non-zero leverage scorings.
+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, and we do not  recommend to increase the threshold to values
+larger than 1E-7. Also using smaller values than 1E-9 does not improve the MLFF if Bayesian regression is used
+(but it can be benficial for SVD).
-== Related Tags and Sections ==
+The description how to choose {{TAG|ML_EPS_LOW}} for accurate force fields is given [[Best practices for machine-learned force fields#Accurate force fields|here]].
-{{TAG|ML_FF_LMLFF}}, {{TAG|ML_FF_MB_MB}}, {{TAG|ML_FF_LBASIS_DISCARD}}, {{TAG|ML_FF_LCONF_DISCARD}}
-{{sc|ML_FF_EPS_LOW|Examples|Examples that use this tag}}
+On the theory of the sparsification of local reference configurations see
+[[Machine learning force field: Theory#Sparsification of local reference configurations|here]].
+== Related tags and articles ==
+{{TAG|ML_LMLFF}}, {{TAG|ML_MB}}, {{TAG|ML_EPS_REG}}, {{TAG|ML_IALGO_LINREG}}
+{{sc|ML_EPS_LOW|Examples|Examples that use this tag}}
 == References ==
@@ Line 16: / Line 26: @@
 ----
-[[Category:INCAR]][[Category:Machine Learning]][[Category:Machine Learned Force Fields]][[Category: Alpha]]
+[[Category:INCAR tag]][[Category:Machine-learned force fields]]