Injectivity of ReLU networks: perspectives from statistical physics
share
When can the input of a ReLU neural network be inferred from its output? In other words, when is the network injective? We consider a single layer, x ↦ReLU(Wx), with a random Gaussian m × n matrix W, in a high-dimensional setting where n, m →∞. Recent work connects this problem to spherical integral geometry giving rise to a conjectured sharp injectivity threshold for α = m/n by studying the expected Euler characteristic of a certain random set. We adopt a different perspective and show that injectivity is equivalent to a property of the ground state of the spherical perceptron, an important spin glass model in statistical physics. By leveraging the (non-rigorous) replica symmetry-breaking theory, we derive analytical equations for the threshold whose solution is at odds with that from the Euler characteristic. Furthermore, we use Gordon's min–max theorem to prove that a replica-symmetric upper bound refutes the Euler characteristic prediction. Along the way we aim to give a tutorial-style introduction to key ideas from statistical physics in an effort to make the exposition accessible to a broad audience. Our analysis establishes a connection between spin glasses and integral geometry but leaves open the problem of explaining the discrepancies.
READ FULL TEXT