Several state-of-the-art methods for isoform identification and quantification are based on sparse probabilistic models, such as Lasso regression. However, explicitly listing the -- possibly exponentially -- large set of candidate transcripts is intractable for genes with many exons. For this reason, existing approaches using sparse models are either restricted to genes with few exons, or only run the regression algorithm on a small set of pre-selected isoforms. We introduce in this paper a new technique, called FlipFlop, based on network flow optimization which can efficiently tackle the sparse estimation problem on the full set of candidate isoforms. By removing the need of preselection step, we obtain better isoform identification while keeping a low computational cost. Experiments with synthetic and real single-end RNA-Seq data confirm that our approach is more accurate than alternatives methods and one of the fastest available.