Trace:

howto:pao-ml

This shows you the differences between two versions of the page.

Both sides previous revision Previous revision | |||

howto:pao-ml [2018/07/19 08:08] oschuett |
howto:pao-ml [2018/10/08 20:05] (current) oschuett |
||
---|---|---|---|

Line 78: | Line 78: | ||

In order to obtain good results from the learning machinery a small number of so-called [[https://en.wikipedia.org/wiki/Hyperparameter | hyperparameters]] have to be carefully tuned for each application. For the current implementation this includes the [[inp>FORCE_EVAL/DFT/LS_SCF/PAO/MACHINE_LEARNING#GP_SCALE| GP_SCALE]] and the descriptor's [[inp>FORCE_EVAL/SUBSYS/KIND/PAO_DESCRIPTOR#BETA | BETA ]] and [[inp>FORCE_EVAL/SUBSYS/KIND/PAO_DESCRIPTOR#SCREENING | SCREENING]]. | In order to obtain good results from the learning machinery a small number of so-called [[https://en.wikipedia.org/wiki/Hyperparameter | hyperparameters]] have to be carefully tuned for each application. For the current implementation this includes the [[inp>FORCE_EVAL/DFT/LS_SCF/PAO/MACHINE_LEARNING#GP_SCALE| GP_SCALE]] and the descriptor's [[inp>FORCE_EVAL/SUBSYS/KIND/PAO_DESCRIPTOR#BETA | BETA ]] and [[inp>FORCE_EVAL/SUBSYS/KIND/PAO_DESCRIPTOR#SCREENING | SCREENING]]. | ||

- | For the optimization of the hyper-parameter exists no gradient, hence one has to use a derivative-free method like the one by [[https://en.wikipedia.org/wiki/Powell%27s_method| Powell]]. A versatile implementation is e.g. the [[src>cp2k/tools/scriptmini/ | scriptmini ]] tool. A good optimization criterion is the variance of the energy difference wrt. the primary basis across the training set. Alternatively, atomic forces could be compared. Despite the missing gradients, this optimization is rather quick because it only performs calculations in the small PAO basis set. | + | For the optimization of the hyper-parameter exists no gradient, hence one has to use a derivative-free method like the one by [[https://en.wikipedia.org/wiki/Powell%27s_method| Powell]]. A versatile implementation is e.g. the [[src>tools/scriptmini | scriptmini ]] tool. A good optimization criterion is the variance of the energy difference wrt. the primary basis across the training set. Alternatively, atomic forces could be compared. Despite the missing gradients, this optimization is rather quick because it only performs calculations in the small PAO basis set. |

===== Step 5: Run simulation with PAO-ML ==== | ===== Step 5: Run simulation with PAO-ML ==== |

howto/pao-ml.txt ยท Last modified: 2018/10/08 20:05 by oschuett

Except where otherwise noted, content on this wiki is licensed under the following license: CC Attribution-ShareAlike 4.0 International