Empirical Bounds on Linear Regions of Deep Rectifier Networks


  • Thiago Serra Bucknell University
  • Srikumar Ramalingam The University of Utah




We can compare the expressiveness of neural networks that use rectified linear units (ReLUs) by the number of linear regions, which reflect the number of pieces of the piecewise linear functions modeled by such networks. However, enumerating these regions is prohibitive and the known analytical bounds are identical for networks with same dimensions. In this work, we approximate the number of linear regions through empirical bounds based on features of the trained network and probabilistic inference. Our first contribution is a method to sample the activation patterns defined by ReLUs using universal hash functions. This method is based on a Mixed-Integer Linear Programming (MILP) formulation of the network and an algorithm for probabilistic lower bounds of MILP solution sets that we call MIPBound, which is considerably faster than exact counting and reaches values in similar orders of magnitude. Our second contribution is a tighter activation-based bound for the maximum number of linear regions, which is particularly stronger in networks with narrow layers. Combined, these bounds yield a fast proxy for the number of linear regions of a deep neural network.




How to Cite

Serra, T., & Ramalingam, S. (2020). Empirical Bounds on Linear Regions of Deep Rectifier Networks. Proceedings of the AAAI Conference on Artificial Intelligence, 34(04), 5628-5635. https://doi.org/10.1609/aaai.v34i04.6016



AAAI Technical Track: Machine Learning