Fragmentation is Efficiently Learnable by Quantum Neural Networks

• URL: http://arxiv.org/abs/2512.00751v2
• Date: Tue, 02 Dec 2025 16:57:47 GMT
• Title: Fragmentation is Efficiently Learnable by Quantum Neural Networks
• Authors: Mikhail Mints, Eric R. Anschuetz,
• Abstract summary: Hilbert space fragmentation is a phenomenon in which the Hilbert space of a quantum system is dynamically decoupled into exponentially many Krylov subspaces.<n>We prove that this transformation can be efficiently learned via gradient descent from a set of training data using quantum neural networks.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Hilbert space fragmentation is a phenomenon in which the Hilbert space of a quantum system is dynamically decoupled into exponentially many Krylov subspaces. We can define the Schur transform as a unitary operation mapping some set of preferred bases of these Krylov subspaces to computational basis states labeling them. We prove that this transformation can be efficiently learned via gradient descent from a set of training data using quantum neural networks, provided that the fragmentation is sufficiently strong such that the summed dimension of the unique Krylov subspaces is polynomial in the system size. To demonstrate this, we analyze the loss landscapes of random quantum neural networks constructed out of Hilbert space fragmented systems. We prove that in this setting, it is possible to eliminate barren plateaus and poor local minima, suggesting efficient trainability when using gradient descent. Furthermore, as the algebra defining the fragmentation is not known a priori and not guaranteed to have sparse algebra elements, to the best of our knowledge there are no existing efficient classical algorithms generally capable of simulating expectation values in these networks. Our setting thus provides a rare example of a physically motivated quantum learning task with no known dequantization.

Related papers

• Grassmann Variational Monte Carlo with neural wave functions [45.935798913942904]
  We formalize the framework introduced by Pfau et al.citepfau2024accurate in terms of Grassmann geometry of the Hilbert space.<n>We validate our approach on the Heisenberg quantum spin model on the square lattice, achieving highly accurate energies and physical observables for a large number of excited states.
  arXiv  Detail & Related papers  (2025-07-14T13:53:13Z)
• Phase-Space Framework for Noisy Intermediate-Scale Quantum Optical Neural Networks [0.904632745647229]
  Quantum optical neural networks (QONNs) enable information processing beyond classical limits.<n>Quantum reservoir performance does not improve monotonously with the number of bosonic modes.<n>Findings are essential for designing and optimising optical bosonic reservoirs for future quantum neuromorphic computing devices.
  arXiv  Detail & Related papers  (2025-07-10T12:07:02Z)
• Trainability of Quantum Models Beyond Known Classical Simulability [1.3941150400549018]
  Variational Quantum Algorithms (VQAs) are promising candidates for near-term quantum computing.<n>They face scalability challenges due to barren plateaus, where vanish exponentially in the system size.<n>Recent conjectures suggest avoiding barren plateaus might inherently lead to classical simulability.
  arXiv  Detail & Related papers  (2025-07-08T19:10:46Z)
• Efficient Learning for Linear Properties of Bounded-Gate Quantum Circuits [62.46800898243033]
  Recent progress in quantum learning theory prompts a question: can linear properties of a large-qubit circuit be efficiently learned from measurement data generated by varying classical inputs?<n>We prove that the sample complexity scaling linearly in $d$ is required to achieve a small prediction error, while the corresponding computational complexity may scale exponentially in d.<n>We propose a kernel-based method leveraging classical shadows and truncated trigonometric expansions, enabling a controllable trade-off between prediction accuracy and computational overhead.
  arXiv  Detail & Related papers  (2024-08-22T08:21:28Z)
• Non-Unitary Quantum Machine Learning [0.0]
  We introduce several probabilistic quantum algorithms that overcome the normal unitary restrictions in quantum machine learning. We show that residual connections between layers of a variational ansatz can prevent barren plateaus in models which would otherwise contain them. We also demonstrate a novel rotationally invariant encoding for point cloud data via Schur-Weyl duality.
  arXiv  Detail & Related papers  (2024-05-27T17:42:02Z)
• Overlapping qubits from non-isometric maps and de Sitter tensor networks [41.94295877935867]
  We show that processes in local effective theories can be spoofed with a quantum system with fewer degrees of freedom. We highlight how approximate overlapping qubits are conceptually connected to Hilbert space dimension verification, degree-of-freedom counting in black holes and holography.
  arXiv  Detail & Related papers  (2023-04-05T18:08:30Z)
• The Hintons in your Neural Network: a Quantum Field Theory View of Deep Learning [84.33745072274942]
  We show how to represent linear and non-linear layers as unitary quantum gates, and interpret the fundamental excitations of the quantum model as particles. On top of opening a new perspective and techniques for studying neural networks, the quantum formulation is well suited for optical quantum computing.
  arXiv  Detail & Related papers  (2021-03-08T17:24:29Z)
• Entanglement Devised Barren Plateau Mitigation [1.382143546774115]
  We implicate random entanglement as the source of barren plateaus and characterize them in terms of many-body entanglement dynamics. We propose and demonstrate a number of barren plateau ameliorating techniques. We find that entanglement limiting, both automatic and engineered, is a hallmark of high-accuracy training.
  arXiv  Detail & Related papers  (2020-12-22T17:49:38Z)
• Entanglement Induced Barren Plateaus [2.8038382295783943]
  We argue that an excess in entanglement between the visible and hidden units in a Quantum Neural Network can hinder learning. We show that quantum neural networks that satisfy a volume-law in the entanglement entropy will give rise to models not suitable for learning with high probability.
  arXiv  Detail & Related papers  (2020-10-29T22:05:30Z)
• The role of boundary conditions in quantum computations of scattering observables [58.720142291102135]
  Quantum computing may offer the opportunity to simulate strongly-interacting field theories, such as quantum chromodynamics, with physical time evolution. As with present-day calculations, quantum computation strategies still require the restriction to a finite system size. We quantify the volume effects for various $1+1$D Minkowski-signature quantities and show that these can be a significant source of systematic uncertainty.
  arXiv  Detail & Related papers  (2020-07-01T17:43:11Z)
• Efficient simulatability of continuous-variable circuits with large Wigner negativity [62.997667081978825]
  Wigner negativity is known to be a necessary resource for computational advantage in several quantum-computing architectures. We identify vast families of circuits that display large, possibly unbounded, Wigner negativity, and yet are classically efficiently simulatable. We derive our results by establishing a link between the simulatability of high-dimensional discrete-variable quantum circuits and bosonic codes.
  arXiv  Detail & Related papers  (2020-05-25T11:03:42Z)

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.