On Representing (Anti)Symmetric Functions

• URL: http://arxiv.org/abs/2007.15298v1
• Date: Thu, 30 Jul 2020 08:23:33 GMT
• Title: On Representing (Anti)Symmetric Functions
• Authors: Marcus Hutter
• Abstract summary: We derive natural approximations in the symmetric case, and approximations based on a single generalized Slater in the anti-symmetric case. We provide a complete and explicit proof of the Equivariant MultiLayer Perceptron, which implies universality of symmetric universalitys and the FermiNet.
• Score: 19.973896010415977
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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 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.

Related papers

• Equivariant Graph Network Approximations of High-Degree Polynomials for Force Field Prediction [62.05532524197309]
  equivariant deep models have shown promise in accurately predicting atomic potentials and force fields in molecular dynamics simulations. In this work, we analyze the equivariant functions for equivariant architecture, and introduce a novel equivariant network, named PACE. As experimented in commonly used benchmarks, PACE demonstrates state-of-the-art performance in predicting atomic energy and force fields.
  arXiv  Detail & Related papers  (2024-11-06T19:34:40Z)
• Exact and Efficient Representation of Totally Anti-Symmetric Functions [11.339994986470895]
  We prove that this ansatz can exactly represent every anti-symmetric and continuous function. The number of basis functions has efficient scaling with respect to dimension.
  arXiv  Detail & Related papers  (2023-11-09T00:03:11Z)
• Refining and relating fundamentals of functional theory [0.0]
  We explain why there exist six equivalent universal functionals, prove concise relations among them and conclude that the important notion of $v$-representability is relative to the scope and choice of variable. For systems with time-reversal symmetry, we explain why there exist six equivalent universal functionals, prove concise relations among them and conclude that the important notion of $v$-representability is relative to the scope and choice of variable.
  arXiv  Detail & Related papers  (2023-01-24T18:09:47Z)
• Kernel-based off-policy estimation without overlap: Instance optimality beyond semiparametric efficiency [53.90687548731265]
  We study optimal procedures for estimating a linear functional based on observational data. For any convex and symmetric function class $mathcalF$, we derive a non-asymptotic local minimax bound on the mean-squared error.
  arXiv  Detail & Related papers  (2023-01-16T02:57:37Z)
• Random Fourier Features for Asymmetric Kernels [24.20121243104385]
  We introduce a complex measure with the real and imaginary parts corresponding to four finite positive measures, which expands the application scope of the Bochner theorem. This framework allows for handling classical symmetric, PD kernels via one positive measure; symmetric, non-positive definite kernels via signed measures; and asymmetric kernels via complex measures. Our AsK-RFFs method is empirically validated on several typical large-scale datasets and achieves promising kernel approximation performance.
  arXiv  Detail & Related papers  (2022-09-18T03:39:18Z)
• Deep Neural Network Approximation of Invariant Functions through Dynamical Systems [15.716533830931766]
  We study the approximation of functions which are invariant with respect to certain permutations of the input indices using flow maps of dynamical systems. Such invariant functions includes the much studied translation-invariant ones involving image tasks, but also encompasses many permutation-invariant functions that finds emerging applications in science and engineering.
  arXiv  Detail & Related papers  (2022-08-18T08:36:16Z)
• Towards Antisymmetric Neural Ansatz Separation [48.80300074254758]
  We study separations between two fundamental models of antisymmetric functions, that is, functions $f$ of the form $f(x_sigma(1), ldots, x_sigma(N)) These arise in the context of quantum chemistry, and are the basic modeling tool for wavefunctions of Fermionic systems.
  arXiv  Detail & Related papers  (2022-08-05T16:35:24Z)
• $O(N^2)$ Universal Antisymmetry in Fermionic Neural Networks [107.86545461433616]
  We propose permutation-equivariant architectures, on which a determinant Slater is applied to induce antisymmetry. FermiNet is proved to have universal approximation capability with a single determinant, namely, it suffices to represent any antisymmetric function. We substitute the Slater with a pairwise antisymmetry construction, which is easy to implement and can reduce the computational cost to $O(N2)$.
  arXiv  Detail & Related papers  (2022-05-26T07:44:54Z)
• A Functional Perspective on Learning Symmetric Functions with Neural Networks [48.80300074254758]
  We study the learning and representation of neural networks defined on measures. We establish approximation and generalization bounds under different choices of regularization. The resulting models can be learned efficiently and enjoy generalization guarantees that extend across input sizes.
  arXiv  Detail & Related papers  (2020-08-16T16:34:33Z)
• Generalized Sliced Distances for Probability Distributions [47.543990188697734]
  We introduce a broad family of probability metrics, coined as Generalized Sliced Probability Metrics (GSPMs) GSPMs are rooted in the generalized Radon transform and come with a unique geometric interpretation. We consider GSPM-based gradient flows for generative modeling applications and show that under mild assumptions, the gradient flow converges to the global optimum.
  arXiv  Detail & Related papers  (2020-02-28T04:18:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.