(MPO)$^2$: Multivariate Polynomial Optimization based on Matrix Product Operators

• URL: http://arxiv.org/abs/2607.15916v1
• Date: Fri, 17 Jul 2026 12:44:48 GMT
• Title: (MPO)$^2$: Multivariate Polynomial Optimization based on Matrix Product Operators
• Abstract summary: We introduce Multi Polynomial based on Matrix Product Operators (MPO)$2$, a framework that combines learned MPO feature embeddings with compact weight tensors.<n>Across regression and classification benchmarks, (MPO)$2$ improves over existing tensor decomposition based models and provides a flexible alternative for efficient function approximation.
• Score: 6.420068890493834
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Central to machine learning and signal processing is the ability to perform universal function approximation and learn complex input-output relationships from limited numbers of observations. Multivariate polynomial models offer a natural way to express such relationships through multiplicative feature interactions, but their coefficient tensors grow exponentially in size with the polynomial degree. Existing tensorized polynomial models reduce this cost, yet canonical polyadic decompositions have rank-limited expressivity, and tensor train formulations are feature order dependent. We introduce Multivariate Polynomial Optimization based on Matrix Product Operators (MPO)$^2$, a framework that combines learned MPO feature embeddings with compact polynomial weight tensors. This yields feature order independent polynomial representations that can incorporate structured operators such as projections, convolutions, and masks for weight tensor symmetries. Across regression and classification benchmarks, (MPO)$^2$ improves over existing tensor decomposition based polynomial models and provides a flexible alternative for efficient polynomial function approximation.

Related papers

• Quantum estimates for classical polynomial optimization [0.0]
  The problem of finding bounds on tensors is both difficult and important given its applications to questions ranging from dynamical stability in complex landscapes to data analysis.<n>From the standpoint of tensor eigenvalue theory, the question is equivalent to finding the smallest and largest eigenvalues of the coefficient corresponding to the given amount.<n>In this essay, a very different strategy, inspired by quantum-mechanical variational methods, is introduced for finding bounds on Stricharts.
  arXiv  Detail & Related papers  (2026-07-28T08:34:11Z)
• PCPOP.jl: A Julia package for partially commutative polynomial optimization [1.389385993711899]
  PCPOP is a Julia package for optimization that supports non-commutative optimization, t-racial optimization, trace optimization and state optimization.<n>PCPOP implements a specialized framework for computations in partially commutative variables that provides significant computational advantages for problems appearing in algebra information.
  arXiv  Detail & Related papers  (2026-07-10T12:20:16Z)
• Constrained Optimal Polynomials for Quantum Linear System Solvers [0.0]
  We introduce constrained optimal approximations as a framework for solving Krylov subspace theory.<n>We develop two classes of solvers: Constrained Uniform Polynomial solvers and Adaptive Polynomial solvers.
  arXiv  Detail & Related papers  (2026-04-22T12:55:15Z)
• When Bayesian Tensor Completion Meets Multioutput Gaussian Processes: Functional Universality and Rank Learning [53.17227599983122]
  Functional tensor decomposition can analyze multi-dimensional data with real-valued indices.<n>We propose a rank-revealing functional low-rank tensor completion (RR-F) method.<n>We establish the universal approximation property of the model for continuous multi-dimensional signals.
  arXiv  Detail & Related papers  (2025-12-25T03:15:52Z)
• $p$-Adic Polynomial Regression as Alternative to Neural Network for Approximating $p$-Adic Functions of Many Variables [55.2480439325792]
  A regression model is constructed that allows approximating continuous functions with any degree of accuracy.<n>The proposed model can be considered as a simple alternative to possible $p$-adic models based on neural network architecture.
  arXiv  Detail & Related papers  (2025-03-30T15:42:08Z)
• The moment polytope of matrix multiplication is not maximal [3.1593341358400737]
  We prove separations between the moment polytopes of matrix multiplication tensors and unit tensors.<n>As a consequence, we find that matrix multiplication moment polytopes are not maximal.<n>We extend these techniques to obtain a new proof of the optimal border subrank bound for matrix multiplication.
  arXiv  Detail & Related papers  (2025-03-28T17:25:06Z)
• 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)
• Exploring the Potential of Polynomial Basis Functions in Kolmogorov-Arnold Networks: A Comparative Study of Different Groups of Polynomials [0.0]
  This paper presents a survey of 18 distincts and their potential applications in Gottliebmogorov Network (KAN) models. The study aims to investigate the suitability of theseDistincts as basis functions in KAN models for complex tasks like handwritten digit classification. The performance metrics of the KAN models, including overall accuracy, Kappa, and F1 score, are evaluated and compared.
  arXiv  Detail & Related papers  (2024-05-30T20:40:16Z)
• Tensor cumulants for statistical inference on invariant distributions [49.80012009682584]
  We show that PCA becomes computationally hard at a critical value of the signal's magnitude. We define a new set of objects, which provide an explicit, near-orthogonal basis for invariants of a given degree. It also lets us analyze a new problem of distinguishing between different ensembles.
  arXiv  Detail & Related papers  (2024-04-29T14:33:24Z)
• PAC Reinforcement Learning for Predictive State Representations [60.00237613646686]
  We study online Reinforcement Learning (RL) in partially observable dynamical systems. We focus on the Predictive State Representations (PSRs) model, which is an expressive model that captures other well-known models. We develop a novel model-based algorithm for PSRs that can learn a near optimal policy in sample complexity scalingly.
  arXiv  Detail & Related papers  (2022-07-12T17:57:17Z)
• Bilinear Classes: A Structural Framework for Provable Generalization in RL [119.42509700822484]
  Bilinear Classes is a new structural framework which permits generalization in reinforcement learning. The framework incorporates nearly all existing models in which a sample complexity is achievable. Our main result provides an RL algorithm which has sample complexity for Bilinear Classes.
  arXiv  Detail & Related papers  (2021-03-19T16:34:20Z)
• Matrix product operator representation of polynomial interactions [0.0]
  We provide an exact construction of interaction Hamiltonians on a one-dimensional lattice which grow as an exponential with the lattice site separation as a matrix product operator (MPO) Our results provide new insight into the correlation structure of many-body quantum operators, and may also be practical in simulations of many-body systems whose interactions are exponentially screened at large.
  arXiv  Detail & Related papers  (2020-01-14T04:15:32Z)

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.