A new cluster algorithm based on invasion percolation is described. Th
e algorithm samples the critical point of a spin system without a prio
ri knowledge of the critical temperature and provides an efficient way
to determine the critical temperature and other observables in the cr
itical region. The method is illustrated for the two- and three-dimens
ional Ising models. The algorithm equilibrates spin configurations muc
h faster than the closely related Swendsen-Wang algorithm.