Fisher-Orthogonal Memory in Quantum Reservoir Computing

• URL: http://arxiv.org/abs/2607.29219v1
• Date: Fri, 31 Jul 2026 09:44:18 GMT
• Title: Fisher-Orthogonal Memory in Quantum Reservoir Computing
• Abstract summary: We introduce a delay-space quantum Fisher information matrix to quantify the distinguishability of memory traces.<n>This perspective identifies Fisher-orthogonal memory as a measurement-efficient design principle.<n>We construct solvable multi-qubit reservoirs based on Clifford routing orbits and Singer-cycle Pauli algebra.
• Score: 4.441368215483203
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Quantum reservoir computing processes temporal information through driven many-body dynamics, but its performance is ultimately limited by how accurately past inputs can be extracted from finite measurements. Here we formulate this limitation as a local multiparameter estimation problem and introduce a delay-space quantum Fisher information matrix to quantify the distinguishability of memory traces. This perspective identifies Fisher-orthogonal memory as a measurement-efficient design principle: different delays should perturb the reservoir state along statistically independent directions. We first analyze the single-qubit limit using the Gill--Massar bound, revealing an optimal write-store-routing trade-off. Guided by this structure, we construct solvable multi-qubit reservoirs based on Clifford routing orbits and Singer-cycle Pauli algebra. The resulting dynamics yield diagonal, analytically programmable Fisher memory matrices with controlled dissipation profiles. Under finite-shot local Pauli readout, these reservoirs retain sharp memory windows and substantially improve over optimized random Ising reservoirs for both linear delay reconstruction and nonlinear product-delay tasks. The nonlinear advantage is traced to second-order response channels that inherit the same Pauli-routing structure. Our results provide an analytically controlled route toward measurement-efficient quantum reservoir computing.

Related papers

• Geometric obstructions to quadratic time scaling in multiparameter quantum estimation [0.8586348698580818]
  Unitary encoding of a single parameter provides quadratic enhancement in precision.<n>However, when estimating multiple parameters simultaneously, this fundamental scaling is not guaranteed.
  arXiv  Detail & Related papers  (2026-07-07T15:40:45Z)
• A hidden bottleneck in classical and quantum linear reservoir computing [0.5161531917413708]
  We identify a hidden bottleneck in the information processing capacity of linear reservoir computers.<n>We show that the capacity available at any fixed delay is limited by what is already present in the preprocessed input.
  arXiv  Detail & Related papers  (2026-05-27T20:25:26Z)
• Clipping Bottleneck: Stabilizing RLVR via Stochastic Recovery of Near-Boundary Signals [83.0127582612634]
  Near-boundary Rescue (NSR) is a minimal, plug-and-play modification that retains out-of-bound tokens to recover lost signals.<n>NSR substantially improves training stability and delivers consistent gains over strong baselines such as DAPO and GSPO.
  arXiv  Detail & Related papers  (2026-05-21T16:45:31Z)
• Evaluating quantum circuits in the reservoir computing paradigm [0.5366467936613012]
  Reservoir computing is a framework used for temporal information processing.<n>We study the effectiveness of a reservoir made using structured brickwall circuits built from two-qubit gates.
  arXiv  Detail & Related papers  (2026-05-02T05:25:27Z)
• Recurrent Quantum Feature Maps for Reservoir Computing [0.6299766708197881]
  We introduce a reservoir based on recurrent quantum feature maps where a fixed quantum circuit is reused to encode both current inputs and a classical feedback signal derived from previous outputs.<n>We evaluate the model on the Mackey-Glass time-series prediction task using our recently introduced CP feature map, and find that it achieves lower mean squared error than standard classical baselines.
  arXiv  Detail & Related papers  (2026-04-03T21:33:10Z)
• Minimal Quantum Reservoirs with Hamiltonian Encoding [72.27323884094953]
  We investigate a minimal architecture for quantum reservoir computing based on Hamiltonian encoding.<n>This approach circumvents many of the experimental overheads typically associated with quantum machine learning.
  arXiv  Detail & Related papers  (2025-05-28T16:50:05Z)
• Refined Risk Bounds for Unbounded Losses via Transductive Priors [67.12679195076387]
  We revisit the sequential variants of linear regression with the squared loss, classification problems with hinge loss, and logistic regression.<n>Our key tools are based on the exponential weights algorithm with carefully chosen transductive priors.
  arXiv  Detail & Related papers  (2024-10-29T00:01:04Z)
• Large-Scale OD Matrix Estimation with A Deep Learning Method [70.78575952309023]
  The proposed method integrates deep learning and numerical optimization algorithms to infer matrix structure and guide numerical optimization. We conducted tests to demonstrate the good generalization performance of our method on a large-scale synthetic dataset.
  arXiv  Detail & Related papers  (2023-10-09T14:30:06Z)
• Solving the time-complexity problem and tuning the performance of quantum reservoir computing by artificial memory restriction [0.0]
  The suitability of quantum reservoir computing for solving temporal tasks is hindered by the collapse of the quantum system when measurements are made. We propose artificially restricting the memory of the quantum reservoir by only using a small number inputs. We numerically study the linear and quadratic algorithms for a fully connected transverse Ising model and a quantum processor model.
  arXiv  Detail & Related papers  (2023-06-22T13:37:34Z)
• Low-rank extended Kalman filtering for online learning of neural networks from streaming data [71.97861600347959]
  We propose an efficient online approximate Bayesian inference algorithm for estimating the parameters of a nonlinear function from a potentially non-stationary data stream. The method is based on the extended Kalman filter (EKF), but uses a novel low-rank plus diagonal decomposition of the posterior matrix. In contrast to methods based on variational inference, our method is fully deterministic, and does not require step-size tuning.
  arXiv  Detail & Related papers  (2023-05-31T03:48:49Z)
• Memory-Efficient Backpropagation through Large Linear Layers [107.20037639738433]
  In modern neural networks like Transformers, linear layers require significant memory to store activations during backward pass. This study proposes a memory reduction approach to perform backpropagation through linear layers.
  arXiv  Detail & Related papers  (2022-01-31T13:02:41Z)

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.