English: A plot used as an illustration of the double descent phenomenon in deep learning in [1] ("test error falls, rises, then falls as a ratio of parameters to data").

From the original publication:

"we plot the training error, test error, bias, and variance as a function of ${\displaystyle \alpha _{p}=N_{p}/M}$ for fixed ${\displaystyle \alpha _{f}<1}$ (more data points ${\displaystyle M}$ than input features ${\displaystyle N_{f}}$ [... for a] Random nonlinear features model (two-layer neural network). Analytic solutions for the ensemble-averaged [...] training error (blue squares) and test error (black circles) [...are] plotted as a function of ${\displaystyle \alpha _{p}=N_{p}/M}$ for fixed ${\displaystyle \alpha _{f}=N_{f}/M=1/4}$. Analytic solutions are indicated as dashed lines with numerical results shown as points. [...] a black dashed line marks the boundary between the under and overparameterized regimes at ${\displaystyle \alpha _{p}=1}$."