Back to GalleryPolynomial Regression
Polynomial Regression transforms input features into polynomial terms (e.g. x², x³, etc.) to fit curved trends. While the feature mappings are non-linear, the model remains linear in its parameters.
Key Parameters & Visual Influence:
• Polynomial Degree: Determines the complexity of the curve. A degree of 1 is a straight line. High degrees (e.g. 5-10) generate multi-bend curves that fit non-linear patterns but risk severe edge oscillations.
• Lambda & L2 Regularization: Penalty terms that shrink high-order coefficients, smoothing out wild curves.
Dataset Studio
CSV format: Headers in first row, last column = label/target. All values must be numeric.
Example: x1, x2, label
Hyperparameters
Polynomial DegreeHighest power exponent used to shape the polynomial curve.3
110
Learning RateStep size taken during gradient descent optimization updates.0.00100
0.000010.1
Max EpochsMaximum training iterations over the dataset.500
505000
RegularizationPenalty style applied to prevent high-order oscillations (L2 Ridge).
4 / 5 parameters active