In a number of estimation problems in bioinformatics, accuracy measures of<br />
the target problem are usually given, and it is important to design estimators<br />
that are suitable to those accuracy measures. However, there is often a<br />
discrepancy between an employed estimator and a given accuracy measure of the<br />
problem. In this study, we introduce a general class of efficient estimators<br />
for estimation problems on high-dimensional binary spaces, which representmany<br />
fundamental problems in bioinformatics. Theoretical analysis reveals that the<br />
proposed estimators generally fit with commonly-used accura...