Explicit function classes are constructed where compositional approximation strictly outperforms superpositional approximation with arbitrarily large gaps.
Topological properties of the set of functions generated by neural networks of fixed size
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.NA 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Compositional Approximation Can Strictly Outperform Superpositional Approximation
Explicit function classes are constructed where compositional approximation strictly outperforms superpositional approximation with arbitrarily large gaps.