Optimization objectives for tabular AutoML models

When you train an AutoML model using a tabular dataset, Vertex AI selects a default optimization objective based on your model type and the data type used for your target column.

The table below provides some details about what kinds of problems each objective is best for:

Classification

Optimization objective API value Use this objective if you want to...
AUC ROC maximize-au-roc Maximize the area under the receiver operating characteristic (ROC) curve. Distinguishes between classes. Default value for binary classification.
Log loss minimize-log-loss Keep prediction probabilities as accurate as possible. Only supported objective for multi-class classification.
AUC PR maximize-au-prc Maximize the area under the precision-recall curve. Optimizes results for predictions for the less common class.
Precision at Recall maximize-precision-at-recall Optimize precision at a specific recall value.
Recall at Precision maximize-recall-at-precision Optimize recall at a specific precision value.

Regression

Optimization objective API value Use this objective if you want to...
RMSE minimize-rmse Minimize root-mean-squared error (RMSE). Captures more extreme values accurately. Default value.
MAE minimize-mae Minimize mean-absolute error (MAE). Views extreme values as outliers with less impact on model.
RMSLE minimize-rmsle Minimize root-mean-squared log error (RMSLE). Penalizes error on relative size rather than absolute value. Useful when both predicted and actual values can be quite large.

Forecasting

Optimization objective API value Use this objective if you want to...
RMSE minimize-rmse Minimize root-mean-squared error (RMSE). Captures more extreme values accurately. Default value.
MAE minimize-mae Minimize mean-absolute error (MAE). Views extreme values as outliers with less impact on model.
RMSLE minimize-rmsle Minimize root-mean-squared log error (RMSLE). Penalizes error on relative size rather than absolute value. Useful when both predicted and actual values can be quite large.
RMSPE minimize-rmspe Minimize root-mean-squared percentage error (RMSPE). Captures a large range of values accurately. Similar to RMSE, but relative to target magnitude. Useful when the range of values is large.
WAPE minimize-wape-mae Minimize the combination of weighted absolute percentage error (WAPE) and mean-absolute-error (MAE). Useful when the actual values are low.
Quantile loss minimize-quantile-loss Minimize the quantile loss at the defined quantiles.