This paper considers H(infinity) control problems involving discrete-t
ime uncertain linear systems. The uncertainty is supposed to belong to
convex-bounded domains, and no additional assumptions are made (as, f
or instance, matching conditions). Two H(infinity) guaranteed cost con
trol problems are solved. The first one concerns the determination of
a state feedback gain (if one exists) in such way the H(infinity) norm
of a certain transfer function remains bounded by a prespecified H(in
finity) level for all possible models. The second one includes this bo
und as an additional variable to be minimized to achieve the smallest
feasible limiting bound. The results follow from the simple geometry o
f those problems which are shown to be convex in the particular parame
tric space under consideration. An example illustrates the theory.