8ccfb1140664a5fa63177fb6e07352f0-Supplemental.pdf

Neural Information Processing Systems 

A.1 Notationandpreliminaries We consider the metric space(X,d( , )) where d : X X R+. We consider`( , ) to be the cross-entropyloss `log(M(x),y), ylogσ(M(x)) (1 y)logσ((1 M(x))) (whereσ(x) = 11+exp( x) isthe sigmoid function) orthe`2 loss.