XGBoost:参数 'objective'设置的是什么？

Question

我想用 XGBoost 解决回归问题。我对学习任务参数目标 [ default=reg:linear ]( XGboost ) 感到困惑，**似乎“目标”用于设置损失函数。**但我无法理解“reg:linear”如何影响损失函数。在逻辑回归演示( XGBoost logistic regression demo )中，objective = binary:logistic 表示损失函数是逻辑损失函数。那么 'objective=reg:linear' 对应哪个损失函数？

Answer 1

So 'objective=reg:linear' corresponds to which loss function?

平方误差

您可以在此处查看逻辑回归和线性回归的损失函数(基于梯度和 hessian)

https://github.com/dmlc/xgboost/blob/master/src/objective/regression_obj.cc

请注意，损失函数相当相似。只是 SecondOrderGradient是平方损失的常数

// common regressions
// linear regression
struct LinearSquareLoss {
  static float PredTransform(float x) { return x; }
  static bool CheckLabel(float x) { return true; }
  static float FirstOrderGradient(float predt, float label) { return predt - label; }
  static float SecondOrderGradient(float predt, float label) { return 1.0f; }
  static float ProbToMargin(float base_score) { return base_score; }
  static const char* LabelErrorMsg() { return ""; }
  static const char* DefaultEvalMetric() { return "rmse"; }
};
// logistic loss for probability regression task
struct LogisticRegression {
  static float PredTransform(float x) { return common::Sigmoid(x); }
  static bool CheckLabel(float x) { return x >= 0.0f && x <= 1.0f; }
  static float FirstOrderGradient(float predt, float label) { return predt - label; }
  static float SecondOrderGradient(float predt, float label) {
    const float eps = 1e-16f;
    return std::max(predt * (1.0f - predt), eps);
  } 

作者在这里提到了这一点 https://github.com/dmlc/xgboost/tree/master/demo/regression