A Tunable Loss Function for Robust Classification: Calibration, Landscape, and Generalization

Tyler Sypherd, Mario Diaz, John Kevin Cava +3

We introduce a tunable loss function called $\alpha$-loss, parameterized by $\alpha \in (0,\infty ]$, which interpolates between the exponential loss ($\alpha =1/2$), the log-loss ($\alpha =1$), and the…