Add a folder containing code examples for loss and constraint sections

doc/source/tutorials/constraint.rst

@@ -55,6 +55,7 @@ Constrains the correlation between predictions and sensitive attributes to be wi
    :name: fair-gallery
 
    ../examples/FairSVM.ipynb
+   ../examples/FaireSVM_new.ipynb
 
 Monotonicity
 ^^^^^^^^^^^^
@@ -73,6 +74,13 @@ Increasing: :math:`\beta_i \le \beta_{i+1}`. Decreasing: :math:`\beta_i \ge \bet
    # Monotonically decreasing
    constraint = [{'name': 'monotonic', 'decreasing': True}]
 
+**Related Example**
+
+.. nblinkgallery::
+   :name: monotonic-gallery
+
+   ../examples/MonotonicSVM.ipynb
+
 Custom Constraints
 ^^^^^^^^^^^^^^^^^^
 Define arbitrary linear constraints of the form :math:`A\beta + b \ge 0`.
@@ -94,6 +102,13 @@ Define arbitrary linear constraints of the form :math:`A\beta + b \ge 0`.
 
    constraint = [{'name': 'custom', 'A': A, 'b': b}]
 
+**Related Example**
+
+.. nblinkgallery::
+   :name: custom-gallery
+
+   ../examples/CustomQR.ipynb
+
 
 References
 ----------

doc/source/tutorials/loss.rst

@@ -35,6 +35,7 @@ Standard Support Vector Machine loss [1]_.
    :name: svm-gallery
 
    ../examples/SVM.ipynb
+   ../examples/SVM_new.ipynb
 
 Smooth SVM
 ^^^^^^^^^^
@@ -53,6 +54,7 @@ A smoothed version of the Hinge loss (using ReHU) that is differentiable everywh
    :name: ssvm-gallery
 
    ../examples/SVM.ipynb
+   ../examples/Smooth_SVM_new.ipynb
 
 Squared SVM
 ^^^^^^^^^^^
@@ -71,6 +73,19 @@ Squared Hinge loss.
    :name: squared-svm-gallery
 
    ../examples/SVM.ipynb
+   ../examples/Squared_SVM_new.ipynb
+
+
+Grid Search for SVM Family
+^^^^^^^^^^^^^^^^^^^^^^^^^^
+Uses ``GridSearchCV`` to select the optimal loss function among SVM, Smooth SVM, and Squared SVM.
+
+**Related Example**
+
+.. nblinkgallery::
+   :name: gridsearch-svm-gallery
+
+   ../examples/GridSearchCV_SVM_losses.ipynb
 
 
 Regression
@@ -94,6 +109,7 @@ Minimizes the check loss (pinball loss) for estimating conditional quantiles [2]
    :name: qr-gallery
 
    ../examples/QR.ipynb
+   ../examples/QR_new.ipynb
 
 Quantile Regression with Epsilon Tolerance
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
@@ -114,6 +130,7 @@ Minimizes the check loss with an epsilon-insensitive zone for robust conditional
    :name: qr-eps-gallery
 
    ../examples/QR_eps.ipynb
+   ../examples/QR_eps_new.ipynb
 
 Huber Regression
 ^^^^^^^^^^^^^^^^
@@ -127,6 +144,13 @@ Robust regression loss that is quadratic for small errors and linear for large e
 
    loss = {'name': 'huber', 'tau': 1.0}
 
+**Related Example**
+
+.. nblinkgallery::
+   :name: huber-gallery
+
+   ../examples/Huber_new.ipynb
+
 Support Vector Regression (SVR)
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 Epsilon-insensitive loss [4]_.
@@ -145,6 +169,7 @@ Epsilon-insensitive loss [4]_.
    :name: svr-gallery
 
    ../examples/SVR.ipynb
+   ../examples/SVR_new.ipynb
 
 Mean Absolute Error (MAE)
 ^^^^^^^^^^^^^^^^^^^^^^^^^
@@ -157,6 +182,13 @@ L1 loss, robust to outliers.
 
    loss = {'name': 'mae'}
 
+**Related Example**
+
+.. nblinkgallery::
+   :name: mae-gallery
+
+   ../examples/MAE_new.ipynb
+
 Mean Squared Error (MSE)
 ^^^^^^^^^^^^^^^^^^^^^^^^
 Standard L2 loss (Least Squares).
@@ -168,6 +200,23 @@ Standard L2 loss (Least Squares).
 
    loss = {'name': 'mse'}
 
+**Related Example**
+
+.. nblinkgallery::
+   :name: mse-gallery
+
+   ../examples/MSE_new.ipynb
+
+Grid Search for Regression Losses
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+Uses ``GridSearchCV`` to select the optimal loss function among Huber, MAE, and MSE.
+
+**Related Example**
+
+.. nblinkgallery::
+   :name: gridsearch-reg-gallery
+
+   ../examples/GridSearchCV_reg_losses.ipynb
 
 References
 ----------