On Representing (Anti)Symmetric Functions

Marcus Hutter

Keywords: Neural network, approximation, universality, Slater determinant, Vandermonde matrix, equivariance, symmetry, anti-symmetry, symmetric polynomials, polarized basis, multilayer perceptron, continuity, smoothness

Abstract: Permutation-invariant, -equivariant, and -covariant functions and anti-symmetric functions are important in quantum physics, computer vision, and other disciplines. Applications often require most or all of the following properties: (a) a large class of such functions can be approximated, e.g. all continuous function (b) only the (anti)symmetric functions can be represented (c) a fast algorithm for computing the approximation (d) the representation itself is continuous or differentiable (e) the architecture is suitable for learning the function from data (Anti)symmetric neural networks have recently been developed and applied with great success. A few theoretical approximation results have been proven, but many questions are still open, especially for particles in more than one dimension and the anti-symmetric case, which this work focuses on. More concretely, we derive natural polynomial approximations in the symmetric case, and approximations based on a single generalized Slater determinant in the anti-symmetric case. Unlike some previous super-exponential and discontinuous approximations, these seem a more promising basis for future tighter bounds.

One-sentence Summary: We prove universality of the symmetric/equivariant 2-hidden-layer Perceptron and of the FermiNet with a single generalized Slater determinant, both based on polynomials and for particles of arbitrary dimension.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=FX1-zRfnSu