An approximate discovery of closed itemsets is usually based on either setting a frequency threshold or computing a sequence of projections. Both approaches, being incremental, do not provide any estimate of the size of the next output and do not ensure that "more interesting patterns" will be generated first. We propose to generate closed item-sets incrementally, w.r.t. the size of the smallest (cardinality-minimal or minimum) generators and show that this approach (i) exhibits anytime property, and (ii) generates itemsets of decreasing quality.