k-factorization and small-x anomalous dimensions

We investigate the consistency requirements of the next-to-leading BFKL equation with the renormalization group, with particular emphasis on running coupling effects and NL anomalous dimensions. We show that, despite some model dependence of the bare hard pomeron, such consistency holds at leading twist level, provided the effective variable alpha(s)(t)log(1/x) is not too large. We give a unified view of resummation formulas for coefficient functions and anomalous dimensions in the eo scheme and we discuss in detail the new one for the <q(q)over bar> contributions to the gluon channel. (C) 1997 Elsevier Science B.V.