LARS (Least Angle Regression)

Hello everyone, we meet again, I'm your friend Quanstack Jun.

Pros and Cons

LARS is a regression algorithm suitable for high-dimensional data.

Advantages:

• It is especially suitable for the case where the feature dimension n is much higher than the number of samples m.
• The worst-case computational complexity of the algorithm is similar to the least squares method, but its computational speed is almost the same as the forward selection algorithm
• A full path can yield piecewise linear results, which is extremely useful in cross-validation of models

Disadvantages:

• Because the iterative direction of LARS is determined according to the residual of the target, the algorithm is extremely sensitive to the noise of the sample.

Publisher: Full-stack programmer, please indicate the source: https://javaforall.cn/124794.htmlOriginal link: https://javaforall.cn