A Function Space View of Bounded Norm Infinite Width ReLU Nets: The Multivariate Case

Sep 25, 2019 Blind Submission readers: everyone Show Bibtex
  • TL;DR: We characterize the space of functions realizable as a ReLU network with an unbounded number of units (infinite width), but where the Euclidean norm of the weights is bounded.
  • Abstract: We give a tight characterization of the (vectorized Euclidean) norm of weights required to realize a function $f:\mathbb{R}\rightarrow \mathbb{R}^d$ as a single hidden-layer ReLU network with an unbounded number of units (infinite width), extending the univariate characterization of Savarese et al. (2019) to the multivariate case.
  • Keywords: inductive bias, regularization, infinite-width networks, ReLU networks
  • Original Pdf:  pdf
0 Replies

Loading