Timezone: »

Exponential Separations in Symmetric Neural Networks
Aaron Zweig · Joan Bruna

Thu Dec 01 02:00 PM -- 04:00 PM (PST) @ Hall J #815
In this work we demonstrate a novel separation between symmetric neural network architectures. Specifically, we consider the Relational Network~\parencite{santoro2017simple} architecture as a natural generalization of the DeepSets~\parencite{zaheer2017deep} architecture, and study their representational gap. Under the restriction to analytic activation functions, we construct a symmetric function acting on sets of size $N$ with elements in dimension $D$, which can be efficiently approximated by the former architecture, but provably requires width exponential in $N$ and $D$ for the latter.

Author Information

Aaron Zweig (New York University)
Joan Bruna (NYU)

More from the Same Authors