[POC] Experimental support for l1 error. (#7812)

Support adaptive tree, a feature supported by both sklearn and lightgbm.  The tree leaf is recomputed based on residue of labels and predictions after construction.

For l1 error, the optimal value is the median (50 percentile).

This is marked as experimental support for the following reasons:
- The value is not well defined for distributed training, where we might have empty leaves for local workers. Right now I just use the original leaf value for computing the average with other workers, which might cause significant errors.
- Some follow-ups are required, for exact, pruner, and optimization for quantile function. Also, we need to calculate the initial estimation.

src/objective/regression_loss.h

@@ -1,5 +1,5 @@
 /*!
- * Copyright 2017-2019 XGBoost contributors
+ * Copyright 2017-2022 XGBoost contributors
  */
 #ifndef XGBOOST_OBJECTIVE_REGRESSION_LOSS_H_
 #define XGBOOST_OBJECTIVE_REGRESSION_LOSS_H_
@@ -38,7 +38,7 @@ struct LinearSquareLoss {
   static const char* DefaultEvalMetric() { return "rmse"; }
 
   static const char* Name() { return "reg:squarederror"; }
-  static ObjInfo Info() { return {ObjInfo::kRegression, true}; }
+  static ObjInfo Info() { return {ObjInfo::kRegression, true, false}; }
 };
 
 struct SquaredLogError {
@@ -65,7 +65,7 @@ struct SquaredLogError {
 
   static const char* Name() { return "reg:squaredlogerror"; }
 
-  static ObjInfo Info() { return {ObjInfo::kRegression, false}; }
+  static ObjInfo Info() { return ObjInfo::kRegression; }
 };
 
 // logistic loss for probability regression task
@@ -102,14 +102,14 @@ struct LogisticRegression {
 
   static const char* Name() { return "reg:logistic"; }
 
-  static ObjInfo Info() { return {ObjInfo::kRegression, false}; }
+  static ObjInfo Info() { return ObjInfo::kRegression; }
 };
 
 // logistic loss for binary classification task
 struct LogisticClassification : public LogisticRegression {
   static const char* DefaultEvalMetric() { return "logloss"; }
   static const char* Name() { return "binary:logistic"; }
-  static ObjInfo Info() { return {ObjInfo::kBinary, false}; }
+  static ObjInfo Info() { return ObjInfo::kBinary; }
 };
 
 // logistic loss, but predict un-transformed margin
@@ -146,7 +146,7 @@ struct LogisticRaw : public LogisticRegression {
 
   static const char* Name() { return "binary:logitraw"; }
 
-  static ObjInfo Info() { return {ObjInfo::kRegression, false}; }
+  static ObjInfo Info() { return ObjInfo::kRegression; }
 };
 
 }  // namespace obj