|Title||Implicit dynamic regularization in deep networks|
|Publication Type||CBMM Memos|
|Year of Publication||2020|
|Authors||Poggio, T, Liao, Q, Xu, M|
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 complements the existing asymptotic analysis for the exponential loss.
- CBMM Funded