Skip to main content

​
softmax_temperature

Controls prediction sharpness (classification only):
  • Lower values (e.g., 0.7): sharper, more confident predictions — useful when accuracy is already high
  • Higher values (e.g., 1.2): softer, more calibrated predictions — useful when probability calibration matters
If you use tuning_config={"calibrate_temperature": True}, the temperature is tuned automatically and overrides this value.

​
Metric Tuning

For metrics that are sensitive to decision thresholds (F1, balanced accuracy, precision, recall), use the built-in metric tuning:

​
Handling Imbalanced Data

  • Set balance_probabilities=True as a quick heuristic for imbalanced datasets when your evaluation metric weights each class equally regardless of its frequency (e.g. balanced accuracy, balanced log loss).
  • For more control, use eval_metric="balanced_accuracy" with threshold tuning
balance_probabilities does not always help. In some cases it can balance predictions at the cost of overall predictive power. Test both settings.

​
n_estimators

n_estimators controls the number of ensemble members. Each estimator uses a different preprocessing configuration, contributing to ensemble diversity and robustness. By default (n_estimators="auto"), TabPFN starts from 8 estimators and automatically increases the count on wide datasets to ensure full feature coverage — the auto-scaled count is capped at 32. To use exactly the number you specify without any auto-scaling, pass an explicit integer. An explicit value is never auto-scaled; TabPFN warns at fit time if it is too small for every feature to be covered.
Passing an explicit n_estimators is useful when you need a fixed, predictable computational budget or when comparing models with a controlled number of estimators.
The auto_scale_n_estimators argument is deprecated and will be removed in v9. Pass an explicit n_estimators instead of setting auto_scale_n_estimators=False.