`

Timezone: »

 
Community Detection and Invariance to Distribution
Guy Bresler

Fri Dec 08 08:05 AM -- 08:40 AM (PST) @

We consider the problem of recovering a hidden community of size K from a graph where edges between members of the community have label X drawn i.i.d. according to P and all other edges have labels drawn i.i.d. according to Q. The information limits for this problem were characterized by Hajek-Wu-Xu in 2016 in terms of the KL-divergence between P and Q. We complement their work by showing that for a broad class of distributions P and Q the computational difficulty is also determined by the KL-divergence. We additionally show how to reduce general P and Q to the case P = Ber(p) and Q = Ber(q) and vice versa, giving a direct computational equivalence (up to polynomial time).

Author Information

Guy Bresler (MIT)

More from the Same Authors