Interpreting Quantum Learning Models via Stochastic Processes

• URL: http://arxiv.org/abs/2607.17327v2
• Date: Sat, 25 Jul 2026 09:28:37 GMT
• Title: Interpreting Quantum Learning Models via Stochastic Processes
• Abstract summary: We develop a framework for representing quantum learning models as processes over configuration spaces.<n>We discuss how such representations of quantum dynamics can be interpreted as walks through a memory space in the spirit of Projective Simulation.
• Score: 0.41510732880787476
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Quantum machine learning models define probabilistic input--output maps through coherent quantum evolution and measurement. While such models can exhibit computational advantages, their internal functioning and decision making generally resists interpretation in terms of stochastic trajectories through intermediate configurations. In contrast to classical (Markovian) stochastic processes, quantum dynamics generically violates the Chapman--Kolmogorov divisibility condition, preventing a decomposition into probabilistically meaningful intermediate transitions. We develop a probabilistic framework for representing quantum learning models as stochastic processes over configuration spaces where the dynamics are modeled as linear maps on probability distributions. Starting from a fixed POVM, arbitrary quantum channels induce transition kernels on the associated probability representation. For informationally complete POVMs, and in particular SIC-POVMs, these kernels are Markovian but generally quasi-stochastic, with non-classicality appearing as negativity. By contrast, projective spaces admit positive stochastic kernels but generally require non-Markovian dynamics due to the failure of Chapman--Kolmogorov divisibility. This yields a trade-off between negativity and dependence on past configurations, i.e. quantum dynamics can be represented either by Markovian quasi-stochastic maps or by positive stochastic processes with higher Markov order. We discuss how such representations of quantum dynamics can be interpreted as stochastic walks through a memory space in the spirit of Projective Simulation, a model of learning and agency in which decisions arise from random walks over an episodic memory network. We further outline how finite-order stochastic kernels can approximate such quantum deliberation processes and show in what regimes the classical machine learning model is recovered.

Related papers

• Quantum simulation of the Liouville equation in classical mechanics with discontinuous potential via Schrödingerization [42.22857110018992]
  We develop quantum simulation algorithms for the Liouville equation of classical mechanics with discontinuous potential.<n>We combine Hamiltonian-preserving schemes by Jin and Wen in Commun. Math. Sci. 3(3), 285-315 (2005) with the Schrdingerization method, which embeds the resulting nonunitary semi-discrete dynamics into a unitary Schrdinger type system.
  arXiv  Detail & Related papers  (2026-06-13T02:49:05Z)
• Quantum Mechanics of Stochastic Systems [0.0954904463032233]
  We develop a fundamental framework for the quantum mechanics of systems.<n>By constructing exact perturbation potentials that transform QHO eigenstates into representations, we demonstrate canonical probability distributions.<n>These results demonstrate that systems are inherently quantum-mechanical in structure, bridging quantum dynamics, statistical physics, and experimental probability realization.
  arXiv  Detail & Related papers  (2025-10-25T20:46:37Z)
• On the Noisy Road to Open Quantum Dynamics: The Place of Stochastic Hamiltonians [0.0]
  evolution underpins several approaches to the dynamics of open quantum systems.<n>In a formulation, the open-system problem is reduced from a coupled system-environment to an effective system-only description.
  arXiv  Detail & Related papers  (2025-10-11T09:40:29Z)
• Path integral approach to quantum thermalization [39.25860941747971]
  We introduce a quasiclassical Green function approach describing the unitary yet irreversible dynamics of quantum systems.<n>We show that it is capable of describing a wide range of system classes and disorder models.<n>We present our formalism in a self-contained and pedagogical manner, aiming to provide a transferable toolbox for the first-principles description of many-body chaotic quantum systems.
  arXiv  Detail & Related papers  (2025-09-07T12:10:48Z)
• Quantum neural ordinary and partial differential equations [38.77776626953413]
  We present a unified framework that brings the continuous-time formalism of classical neural ODEs/PDEs into quantum machine learning and quantum control.<n>We define QNODEs as the evolution of finite-dimensional quantum systems, and QNPDEs as infinite-dimensional (continuous-variable) counterparts.
  arXiv  Detail & Related papers  (2025-08-24T18:43:44Z)
• Quantum Systems as Indivisible Stochastic Processes [0.0]
  According to the generalization-quantum correspondence, a quantum system can be understood as a process unfolding in an old-fashioned configuration space based on ordinary notions of probability and indivisible' laws.<n>This paper initiates a deeper investigation into the conceptual foundations and structure of the generalization-quantum correspondence.
  arXiv  Detail & Related papers  (2025-07-27T22:08:28Z)
• Overcoming Dimensional Factorization Limits in Discrete Diffusion Models through Quantum Joint Distribution Learning [79.65014491424151]
  We propose a quantum Discrete Denoising Diffusion Probabilistic Model (QD3PM)<n>It enables joint probability learning through diffusion and denoising in exponentially large Hilbert spaces.<n>This paper establishes a new theoretical paradigm in generative models by leveraging the quantum advantage in joint distribution learning.
  arXiv  Detail & Related papers  (2025-05-08T11:48:21Z)
• Evaluation of phase shifts for non-relativistic elastic scattering using quantum computers [39.58317527488534]
  This work reports the development of an algorithm that makes it possible to obtain phase shifts for generic non-relativistic elastic scattering processes on a quantum computer.
  arXiv  Detail & Related papers  (2024-07-04T21:11:05Z)
• The Stochastic-Quantum Correspondence [0.0]
  This paper argues that every quantum system can be understood as a sufficiently general kind of unfolding process in an old-fashioned configuration space according to ordinary notions of probability.<n>At a more practical level, the quasi-quantum correspondence leads to a novel reconstruction of quantum theory, alongside the Hilbert-space, path-integral, andprobability representations, and also provides a framework for using Hilbert-space methods to formulate highly generic, non-Markovian types of dynamics.
  arXiv  Detail & Related papers  (2023-02-20T04:11:05Z)
• Quantum Tensor Networks, Stochastic Processes, and Weighted Automata [31.641069053835192]
  Similar models have been studied in the processes and weighted automata literature. We show how stationary or uniform versions of popular quantum tensor network models have equivalent representations in the processes and weighted automata literature.
  arXiv  Detail & Related papers  (2020-10-20T22:28:50Z)
• Minimal informationally complete measurements for probability representation of quantum dynamics [0.0]
  We suggest an approach for describing dynamics of finite-dimensional quantum systems in terms of pseudostochastic maps acting on probability distributions. A key advantage of the suggested approach is that minimal informationally complete positive operator-valued measures (MIC-POVMs) are easier to construct in comparison with their symmetric versions (SIC-POVMs) We apply the MIC-POVM-based probability representation to the digital quantum computing model.
  arXiv  Detail & Related papers  (2020-06-22T13:19:23Z)

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.