User Tools

Site Tools


howto:pao-ml

Differences

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

Link to this comparison view

Both sides previous revision Previous revision
howto:pao-ml [2018/07/19 10:08]
oschuett
howto:pao-ml [2018/10/08 22:05] (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.1531987703.txt.gz ยท Last modified: 2018/07/19 10:08 by oschuett