2000 character limit reached
Error bounds for deep ReLU networks using the Kolmogorov--Arnold superposition theorem (1906.11945v2)
Published 27 Jun 2019 in math.NA, cs.LG, and cs.NA
Abstract: We prove a theorem concerning the approximation of multivariate functions by deep ReLU networks, for which the curse of the dimensionality is lessened. Our theorem is based on a constructive proof of the Kolmogorov--Arnold superposition theorem, and on a subset of multivariate continuous functions whose outer superposition functions can be efficiently approximated by deep ReLU networks.
Collections
Sign up for free to add this paper to one or more collections.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.