Partial information decomposition (PID) splits the information that two sources carry about a target into redundant, unique and synergistic parts, with nonnegative decompositions lying on a segment where redundancy measures are bounded by the positive part of the co-information and the smaller source-target information. We parameterize this segment by the overlap, the common excess of redundancy and synergy over their net balance, and show that for many of the named PID measures, their redundancy can be written as the largest positive part of the co-information over a set of reference distributions. This common form induces an ordering of those PIDs on the segment. With the smallest redundancy and synergy and the largest unique atoms of any nonnegative PID, the information-theoretic version of Hi-Fi, a feature-importance method, is the zero-overlap end of the segment for two sources, with the maximum overlap bound given by the minimum mutual information (MMI) PID. We introduce, by splitting the co-information into a pairwise maximum- entropy part and the third-order connected information, a PID that sits at zero overlap except when pairwise redundancy and triadic synergy coexist. For three or more sources the bivariate results hold on every pair of merged source groups, and among all nonnegative solutions of the lattice equations MMI and Hi-Fi still give the smallest and largest unique atoms but zero overlap on all pairs at once is often unattainable. Two inequalities across pairs are necessary in general and sufficient for three sources. For identity targets zero overlap is possible exactly when the sources' information diagram is nonnegative. In random three- and four-source distributions zero overlap on all pairs fails in 21-100% of the cases.

翻译：暂无翻译