Implicit dynamic regularization in deep networks
Author(s)Poggio, Tomaso; Liao, Qianli
Square loss has been observed to perform well in classification tasks, at least as well as crossentropy. However, a theoretical justification is lacking. Here we develop a theoretical analysis for the square loss that also complements the existing asymptotic analysis for the exponential loss.
Center for Brains, Minds and Machines (CBMM)