Fig. 2From: Seagull: lasso, group lasso and sparse-group lasso regularization for linear regression models via proximal gradient descentPath of mean squared error (MSE) of predicted age for each λ. Results of seagull and SGL are represented in blue and violet, respectively. The vertical lines mark the index in the sequence of λ’s with lowest MSE in corresponding color. The respective lowest MSE of seagull and SGL were 11.79 and 12.78Back to article page