Tensor network representations of discrete maximum entropy distributions via mean polytopes

• URL: http://arxiv.org/abs/2609.07184v1
• Date: Mon, 07 Sep 2026 08:14:54 GMT
• Title: Tensor network representations of discrete maximum entropy distributions via mean polytopes
• Abstract summary: We present tensor network representations for discrete maximum entropy distributions under expectation constraints.<n>By leveraging the geometry of the convex polytope of realizable expectation vectors, we represent any maximum entropy distribution in the same architecture.<n>We derive explicit representations for the support within the CompActNet architecture.
• Score: 0.8021197489470758
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present tensor network representations for discrete maximum entropy distributions under expectation constraints. To this end, we introduce Computation-Activation Networks (CompActNets), a tensor network architecture that subsumes exponential families. By leveraging the geometry of the convex polytope of realizable expectation vectors, we represent any maximum entropy distribution in the same architecture. We exploit the fact that proper faces of this polytope correspond to the boundary closure of exponential families, which restricts the distribution's support. We then derive explicit representations for the support within the CompActNet architecture. The proposed framework suggests tensor network ranks as complexity measures for faces. Finally, a case study on Boolean statistics links the geometry of 0/1-polytopes directly to propositional formulas.

Related papers

• Representational Capacity: Geometric Limits on Feature Representation in Transformer Language Models [51.56484100374058]
  We develop a framework for estimating how many near-orthogonal directions a model can support.<n>Applying this metric across dozens of open-source models reveals two classes: models with high $varepsilon$ whose embeddings lack near-orthogonal structure, and models with low $varepsilon$ that maintain it.
  arXiv  Detail & Related papers  (2026-06-01T18:28:56Z)
• Graph Signal Diffusion Models for Wireless Resource Allocation [74.84410305593006]
  We consider constrained ergodic resource optimization in wireless networks with graph-structured interference.<n>We show that time-sharing the generated power allocations achieves near-optimal ergodic sum-rate utility and near-feasible ergodic minimum-rates.
  arXiv  Detail & Related papers  (2026-04-06T21:12:25Z)
• Vertex structure of fiber products of probability polytopes [0.0]
  We develop tools for characterizing vertices of fiber products of polytopes.<n>In the theory of simplicial distributions, a pair of simplicial sets encoding measurement and outcome spaces determines a convex polytope.
  arXiv  Detail & Related papers  (2026-03-19T21:21:08Z)
• Canonical partial ordering from min-cuts and quantum entanglement in random tensor networks [5.882601249202242]
  We show that the emphfinite correction to entanglement R'enyi entropy arising from the degeneracy of the min-cuts is given by the number of emphorder morphisms<n>We also show that the number of order morphisms corresponds to moments of a graph-dependent measure which generalizes the free Bessel law in some special cases in free probability theory.
  arXiv  Detail & Related papers  (2025-06-30T14:26:40Z)
• Input convex neural networks: universal approximation theorem and implementation for isotropic polyconvex hyperelastic energies [0.0]
  This paper presents a novel framework that enforces necessary physical and mathematical constraints while simultaneously satisfying the universal mathematical constraints.<n>A universal theorem for the proposed approach is proven.<n>The proposed network can any frame-in, isotropic poly energy (provided the network is large)<n>Existing approaches identify the advantages of the proposed method.
  arXiv  Detail & Related papers  (2025-02-12T16:15:03Z)
• Conditional Distribution Quantization in Machine Learning [83.54039134248231]
  Conditional expectation mathbbE(Y mid X) often fails to capture the complexity of multimodal conditional distributions mathcalL(Y mid X)<n>We propose using n-point conditional quantizations--functional mappings of X that are learnable via gradient descent--to approximate mathcalL(Y mid X)
  arXiv  Detail & Related papers  (2025-02-11T00:28:24Z)
• SpaceMesh: A Continuous Representation for Learning Manifold Surface Meshes [61.110517195874074]
  We present a scheme to directly generate manifold, polygonal meshes of complex connectivity as the output of a neural network.<n>Our key innovation is to define a continuous latent connectivity space at each mesh, which implies the discrete mesh.<n>In applications, this approach not only yields high-quality outputs from generative models, but also enables directly learning challenging geometry processing tasks such as mesh repair.
  arXiv  Detail & Related papers  (2024-09-30T17:59:03Z)
• A Max-Flow approach to Random Tensor Networks [0.40964539027092906]
  We study the entanglement entropy of a random tensor network (RTN) using tools from free probability theory. One can think of random tensor networks are specific probabilistic models for tensors having some particular geometry dictated by a graph (or network) structure.
  arXiv  Detail & Related papers  (2024-07-02T18:00:01Z)
• Data Topology-Dependent Upper Bounds of Neural Network Widths [52.58441144171022]
  We first show that a three-layer neural network can be designed to approximate an indicator function over a compact set. This is then extended to a simplicial complex, deriving width upper bounds based on its topological structure. We prove the universal approximation property of three-layer ReLU networks using our topological approach.
  arXiv  Detail & Related papers  (2023-05-25T14:17:15Z)
• Holographic properties of superposed quantum geometries [0.0]
  We study the holographic properties of a class of quantum geometry states characterized by a superposition of discrete geometric data. This class includes spin networks, the kinematic states of lattice gauge theory and discrete quantum gravity.
  arXiv  Detail & Related papers  (2022-07-15T17:37:47Z)
• Superposed Random Spin Tensor Networks and their Holographic Properties [0.0]
  We study boundary-to-boundary holography in a class of spin network states defined by analogy to projected entangled pair states (PEPS) We consider superpositions of states corresponding to well-defined, discrete geometries on a graph.
  arXiv  Detail & Related papers  (2022-05-19T12:24:57Z)
• On Infinite-Width Hypernetworks [101.03630454105621]
  We show that hypernetworks do not guarantee to a global minima under descent. We identify the functional priors of these architectures by deriving their corresponding GP and NTK kernels. As part of this study, we make a mathematical contribution by deriving tight bounds on high order Taylor terms of standard fully connected ReLU networks.
  arXiv  Detail & Related papers  (2020-03-27T00:50:29Z)

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.