RENORMALIZATION OF GAUGE-INVARIANT COMPOSITE-OPERATORS IN THE LIGHT-CONE GAUGE

We generalise to composite operators concepts and techniques which have been successful in proving renormalization of the effective action in the light-cone gauge. Gauge-invariant operators can be grouped into classes, closed under a matrixwise renormalization. In spite of the presence of nonlocal counterterms, an ''effective'' dimensional hierarchy still guarantees that any class is endowed with a finite number of elements. The main result we find is that gauge-invariant operators under renormalization mix only among themselves, thanks to the very simple structure of Lee-Ward identities in this gauge, contrary to their behavior in covariant gauges.