Rethinking Quantum Continual Learning with Quantum Fisher Information

• URL: http://arxiv.org/abs/2607.16030v1
• Date: Fri, 17 Jul 2026 15:02:32 GMT
• Title: Rethinking Quantum Continual Learning with Quantum Fisher Information
• Abstract summary: Quantum continual learning aims to train quantum models on sequential tasks without losing previously learned knowledge.<n>We propose quantum elastic weight consolidation (QEWC), a quantum Fisher information (QFI)-informed regularization method for mitigating forgetting.
• Score: 2.1320486231868068
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Quantum continual learning aims to train quantum models on sequential tasks without losing previously learned knowledge. However, variational quantum classifiers (VQCs) are prone to catastrophic forgetting under nonstationary task distributions. We propose quantum elastic weight consolidation (QEWC), a quantum Fisher information (QFI)-informed regularization method for mitigating forgetting. Unlike conventional elastic weight consolidation based on classical Fisher information (CFI), which measures parameter importance through measurement-dependent output statistics, QEWC uses QFI to quantify the intrinsic sensitivity of the parameterized quantum state. This gives an information-geometric view in which important parameters are identified by the local response of the quantum state manifold. We evaluate QEWC on VQCs trained on sequential binary classification tasks, including classical image-classification and quantum phase-classification tasks. Simulations show that sequential training without regularization causes severe forgetting, while both CFI-based EWC and QFI-based QEWC improve retention of previous tasks. Mechanistic analyses further show that the two methods impose different regularization geometries: CFI acts selectively on measurement-sensitive directions, whereas QFI imposes a denser state-geometric constraint over parameter space. Under depolarizing noise, CFI values are strongly suppressed by degraded measurement statistics, while QFI preserves a more stable sensitivity structure of the noisy parameterized quantum state. These results establish QEWC as a physically motivated approach for studying and mitigating forgetting in quantum continual learning through quantum-state geometry.

Related papers

• Machine-Learning Prediction of Quantum Fisher Information from Collective Spin and Spectral Features [0.0]
  We investigate the extent to which Quantum Fisher information can be predicted from a limited set of experimentally accessible quantities.<n>By comparing different physically motivated features, we identify a dominant feature set governing QFI.<n>We demonstrate that QFI is governed primarily by the interplay between collective covariance and low-order spectral moments of the density matrix.
  arXiv  Detail & Related papers  (2026-06-02T00:45:09Z)
• Quantum timekeeping and the dynamics of scrambling in critical systems [0.0]
  We show that local subsystems of information scrambling systems naturally function as quantum stopwatches.<n>Treating time as the estimation parameter, we derive a generalized quantum Cramer-Rao bound.<n>Using a scaling analysis based on imaginary-time correlators, we show that the subsystem QFI exhibits universal critical amplification near quantum phase transitions.
  arXiv  Detail & Related papers  (2026-03-13T14:21:49Z)
• Fragility of Optimal Measurements due to Noise in Probe States for Quantum Sensing [0.0]
  We show how discontinuities increase fragility through Jensen's inequality.<n>We present a framework for understanding how discontinuities increase fragility through Jensen's inequality.
  arXiv  Detail & Related papers  (2026-01-13T16:39:41Z)
• Continual Quantum Architecture Search with Tensor-Train Encoding: Theory and Applications to Signal Processing [68.35481158940401]
  CL-QAS is a continual quantum architecture search framework.<n>It mitigates challenges of costly encoding amplitude and forgetting in variational quantum circuits.<n>It achieves controllable robustness expressivity, sample-efficient generalization, and smooth convergence without barren plateaus.
  arXiv  Detail & Related papers  (2026-01-10T02:36:03Z)
• Towards Quantum Enhanced Adversarial Robustness with Rydberg Reservoir Learning [45.92935470813908]
  Quantum computing reservoir (QRC) leverages the high-dimensional, nonlinear dynamics inherent in quantum many-body systems.<n>Recent studies indicate that perturbation quantums based on variational circuits remain susceptible to adversarials.<n>We investigate the first systematic evaluation of adversarial robustness in a QR based learning model.
  arXiv  Detail & Related papers  (2025-10-15T12:17:23Z)
• VQC-MLPNet: An Unconventional Hybrid Quantum-Classical Architecture for Scalable and Robust Quantum Machine Learning [50.95799256262098]
  Variational quantum circuits (VQCs) hold promise for quantum machine learning but face challenges in expressivity, trainability, and noise resilience.<n>We propose VQC-MLPNet, a hybrid architecture where a VQC generates the first-layer weights of a classical multilayer perceptron during training, while inference is performed entirely classically.
  arXiv  Detail & Related papers  (2025-06-12T01:38:15Z)
• Potential and limitations of quantum extreme learning machines [55.41644538483948]
  We present a framework to model QRCs and QELMs, showing that they can be concisely described via single effective measurements. Our analysis paves the way to a more thorough understanding of the capabilities and limitations of both QELMs and QRCs.
  arXiv  Detail & Related papers  (2022-10-03T09:32:28Z)
• Variational Quantum Algorithm for Estimating the Quantum Fisher Information [0.0]
  We present a variational quantum algorithm called Variational Quantum Fisher Information Estimation (VQFIE) By estimating lower and upper bounds on the QFI, based on bounding the fidelity, VQFIE outputs a range in which the actual QFI lies. This result can then be used to variationally prepare the state that maximizes the QFI, for the application of quantum sensing.
  arXiv  Detail & Related papers  (2020-10-20T17:44:55Z)
• Using Quantum Metrological Bounds in Quantum Error Correction: A Simple Proof of the Approximate Eastin-Knill Theorem [77.34726150561087]
  We present a proof of the approximate Eastin-Knill theorem, which connects the quality of a quantum error-correcting code with its ability to achieve a universal set of logical gates. Our derivation employs powerful bounds on the quantum Fisher information in generic quantum metrological protocols.
  arXiv  Detail & Related papers  (2020-04-24T17:58:10Z)
• In and out of equilibrium quantum metrology with mean-field quantum criticality [68.8204255655161]
  We study the influence that collective transition phenomena have on quantum metrological protocols. The single spherical quantum spin (SQS) serves as stereotypical toy model that allows analytical insights on a mean-field level.
  arXiv  Detail & Related papers  (2020-01-09T19:20:42Z)

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.