Efficient Representation of multicategorical local Hilbert spaces: nonlinear Restricted Boltzmann Machines to Kolmogorov-Arnold Networks

• URL: http://arxiv.org/abs/2609.06672v2
• Date: Fri, 11 Sep 2026 10:45:42 GMT
• Title: Efficient Representation of multicategorical local Hilbert spaces: nonlinear Restricted Boltzmann Machines to Kolmogorov-Arnold Networks
• Abstract summary: Neural network quantum states (NQS) for representing spin-$frac12$ systems are typically built from Multi-Layer Perceptrons (MLPs) with binary visible variables.<n>I find numerically that allowing $log $ to be a nonlinear function of the raw multi-valued spin variable is a natural categorical generalization.<n>I demonstrate that this framework captures the critical behaviour of the quantum Potts Hamiltonian, recovering its phase transition.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Neural network quantum states (NQS) for representing spin-$\frac{1}{2}$ systems are typically built from Multi-Layer Perceptrons (MLPs) with binary visible variables, in which the input spins are first combined through linear affine maps before more expressive nonlinear transformations are applied. The standard way for representing multi-categorical systems, namely spin-1 and spin-2, or the q-state quantum Potts systems with more than two local degrees of freedom, is a unary or one-hot encoded MLP architecture. Following a few similar studies, I observe that while the one-hot construction is the mathematically faithful encoding for systems with more than two local states such as spin-$S$ models with $S > 1/2$ or $q$-state Potts models, its parameter count grows with the number of local states, and the resulting optimization landscape can hinder convergence. I find numerically that allowing $\log Ψ$ to be a nonlinear function of the raw multi-valued spin variable is a natural categorical generalization: it preserves the labelling freedom of the local basis and reproduces the one-hot model with strictly fewer parameters, often with improved trainability. I first benchmark this idea on shallow Restricted Boltzmann Machines (RBMs), equipping them with several distinct nonlinear connections, for spin-1, 2, and 3 Heisenberg chains. I then turn to Kolmogorov-Arnold Networks (KANs), where each edge carries a learnable univariate nonlinearity, and show that they provide a strictly more expressive realization of the same principle. Finally, I demonstrate that this framework captures the critical behaviour of the quantum Potts Hamiltonian, recovering its phase transition.

Related papers

• Extending the Bloch sphere model to an N-qubit system [63.01002236320087]
  We propose a novel geometric model extending the Bloch sphere representation to arbitrary $N$-qubit systems.<n>We demonstrate that any pure 2-qubit state is uniquely described by three spheres: two for individual qubits and a third encapsulating bipartite entanglement.
  arXiv  Detail & Related papers  (2026-07-06T12:14:04Z)
• Neural Network Quantum Field Theory from Transformer Architectures [0.0]
  We propose a neural-network construction of Euclidean scalar quantum field theories from transformer attention heads.<n>For a single attention head, shared random softmax weights couple different width coordinates and induce non-Gaussian field statistics.<n>We show that summing many independent heads with standard $1/N_h$ normalization suppresses connected non-Gaussian correlators as $1/N_h$, yielding a Gaussian NN-QFT in the large-head limit.
  arXiv  Detail & Related papers  (2026-02-10T19:02:03Z)
• FFT-Accelerated Auxiliary Variable MCMC for Fermionic Lattice Models: A Determinant-Free Approach with $O(N\log N)$ Complexity [52.3171766248012]
  We introduce a Markov Chain Monte Carlo (MCMC) algorithm that dramatically accelerates the simulation of quantum many-body systems.<n>We validate our algorithm on benchmark quantum physics problems, accurately reproducing known theoretical results.<n>Our work provides a powerful tool for large-scale probabilistic inference and opens avenues for physics-inspired generative models.
  arXiv  Detail & Related papers  (2025-10-13T07:57:21Z)
• Hybrid between biologically inspired and quantum inspired many-body states [0.0]
  We construct variational many-body ansatz from a simple network of perceptrains.<n>The network can be thought of as a neural network with a few distinct features inherited from tensor networks.
  arXiv  Detail & Related papers  (2025-06-05T13:57:48Z)
• Probing Quantum Spin Systems with Kolmogorov-Arnold Neural Network Quantum States [0.0]
  We propose textttSineKAN, a neural network model to represent quantum mechanical wave functions.<n>We find that textttSineKAN models can be trained to high precisions and accuracies with minimal computational costs.
  arXiv  Detail & Related papers  (2025-06-02T17:18:40Z)
• Learning with Norm Constrained, Over-parameterized, Two-layer Neural Networks [54.177130905659155]
  Recent studies show that a reproducing kernel Hilbert space (RKHS) is not a suitable space to model functions by neural networks. In this paper, we study a suitable function space for over- parameterized two-layer neural networks with bounded norms.
  arXiv  Detail & Related papers  (2024-04-29T15:04:07Z)
• Transformers as Support Vector Machines [54.642793677472724]
  We establish a formal equivalence between the optimization geometry of self-attention and a hard-margin SVM problem. We characterize the implicit bias of 1-layer transformers optimized with gradient descent. We believe these findings inspire the interpretation of transformers as a hierarchy of SVMs that separates and selects optimal tokens.
  arXiv  Detail & Related papers  (2023-08-31T17:57:50Z)
• Bounding the Width of Neural Networks via Coupled Initialization -- A Worst Case Analysis [121.9821494461427]
  We show how to significantly reduce the number of neurons required for two-layer ReLU networks. We also prove new lower bounds that improve upon prior work, and that under certain assumptions, are best possible.
  arXiv  Detail & Related papers  (2022-06-26T06:51:31Z)
• Neural-network Quantum States for Spin-1 systems: spin-basis and parameterization effects on compactness of representations [0.0]
  Neural network quantum states (NQS) have been widely applied to spin-1/2 systems where they have proven to be highly effective. We propose a more direct generalisation of RBMs for spin-1 that retains the key properties of the standard spin-1/2 RBM. Further to this we investigate how the hidden unit complexity of NQS depend on the local single-spin basis used.
  arXiv  Detail & Related papers  (2021-05-18T15:05:22Z)
• Neural Networks are Convex Regularizers: Exact Polynomial-time Convex Optimization Formulations for Two-layer Networks [70.15611146583068]
  We develop exact representations of training two-layer neural networks with rectified linear units (ReLUs) Our theory utilizes semi-infinite duality and minimum norm regularization.
  arXiv  Detail & Related papers  (2020-02-24T21:32:41Z)

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.