search

owenodriscoll / AutoML

Python package for automated hyperparameter-optimization of common machine-learning algorithms
MIT License
2 stars 0 forks source link

train multiple weak predictors #10

Open owenodriscoll opened 1 year ago

owenodriscoll commented 1 year ago

instead of dedicating significant resources towards hyper-optimizing each regressor, train several of the same regressors (e.g. not lightgbm, xgboost, etc but lightgbm_0, lightgbm_1, lightgbm_2, xgboost_0, xgboost_1, xgboost_2 etc) with less resources. Thereby the stacking regressor has more information available by using more weak predictors which, though individually worse might contain more unique information, rather than several good predictors, which likely contain duplicate information.

owenodriscoll commented 1 year ago

Perhaps by adding a method which not only selects best regressors but the best single regressor plus N random other regressors in: https://github.com/owenodriscoll/AutoML/blob/b2a83c5760903e85721d9e6cfdf98cae2fe4590d/AutoML/automl.py#L423

owenodriscoll commented 1 year ago

Add

  1. functionality to find best weak predictors to include
  2. way to provide which weak predictors to include (rather than only randomly select n)