NeurIPS 2020

Rankmax: An Adaptive Projection Alternative to the Softmax Function

Meta Review

Three knowledgeable referees support acceptance for the contributions. One reviewer (R1) was slightly on the reject side but I discounted that review because of low confidence. Therefore I recommend acceptance. However, please consider revising your paper to include suggested references, as also promised in the rebuttal, and if possible also extend your empirical evaluation.