LinearSVR

#include <Skigen/SVM>

template <typename Scalar = double>
class Skigen::LinearSVR(C=1.0, epsilon=0, loss=Loss::EpsilonInsensitive, tol=1e-4, max_iter=1000, fit_intercept=true, random_state=std::nullopt)

Linear epsilon-insensitive Support Vector Regression.

Mirrors sklearn.svm.LinearSVR.

Solves $\min_w \tfrac{1}{2}\|w\|^2 + C \sum_i L(y_i - w \cdot x_i - b)$ where $L$ is the $\epsilon$-insensitive loss (loss="epsilon_insensitive", the sklearn default) — the residual contributes only when $|r| > \epsilon$.

---

---

Attributes:

• C : Scalar

• epsilon : Scalar

• coef : RowVectorType

• intercept : Scalar

---

Methods

SKIGEN_PARAMS()

---

fit(X, y)

Fit from a sparse design matrix (densifies internally).

---

predict(X)

---

score(X, y)

---