# On Representing (Anti)Symmetric Functions

arXiv: https://arxiv.org/abs/2007.15298 · HTML: https://mlsanity.com/paper/2007.15298/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jul 2020.

## Built on by (most cited first, 12 of 12)

- [Ab-Initio Potential Energy Surfaces by Pairing GNNs with Neural Wave Functions](https://mlsanity.com/paper/2110.05064/) (2021)
- [Sumformer: Universal Approximation for Efficient Transformers](https://mlsanity.com/paper/2307.02301/) (2023)
- [Ab-initio quantum chemistry with neural-network wavefunctions](https://mlsanity.com/paper/2208.12590/) (2022)
- [Explicitly antisymmetrized neural network layers for variational Monte Carlo simulation](https://mlsanity.com/paper/2112.03491/) (2021)
- [Symmetric and antisymmetric kernels for machine learning problems in quantum physics and chemistry](https://mlsanity.com/paper/2103.17233/) (2021)
- [Equilibrium Aggregation: Encoding Sets via Optimization](https://mlsanity.com/paper/2202.12795/) (2022)
- [Bi-Lipschitz Ansatz for Anti-Symmetric Functions](https://mlsanity.com/paper/2503.04263/) (2025)
- [Towards Antisymmetric Neural Ansatz Separation](https://mlsanity.com/paper/2208.03264/) (2022)
- [Anti-symmetric Barron functions and their approximation with sums of determinants](https://mlsanity.com/paper/2303.12856/) (2023)
- [Sorting Out Quantum Monte Carlo](https://mlsanity.com/paper/2311.05598/) (2023)
- [On the Dimension-Free Approximation of Deep Neural Networks for Symmetric Korobov Functions](https://mlsanity.com/paper/2511.12398/) (2025)
- [On the Universality of Transformer Architectures; How Much Attention Is Enough?](https://mlsanity.com/paper/2512.18445/) (2025)

## Abstract (arXiv)

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 focusses 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. We provide a complete and explicit universality proof of the Equivariant MultiLayer Perceptron, which implies universality of symmetric MLPs and the FermiNet.