Stable Self-Modulating Quantum Fast-Weight Programmers with Bounded Memory Gates

• URL: http://arxiv.org/abs/2607.02363v1
• Date: Thu, 02 Jul 2026 16:06:04 GMT
• Title: Stable Self-Modulating Quantum Fast-Weight Programmers with Bounded Memory Gates
• Abstract summary: Quantum Fast-Weights Programmer (QFWP) store temporal information in dynamically programmed variational-circuit parameters.<n>Self-Modulating QFWP improves this framework by using input-dependent gates for both new fast-weight updates and the accumulated fast-weight state.<n>We show that old-state modulation is the most consistent source of improvement over Standard QFWP.
• Score: 36.26005687010788
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Quantum Fast-Weight Programmers (QFWPs) store temporal information in dynamically programmed variational-circuit parameters rather than in nonlinear recurrent hidden states, offering a practical route to quantum sequence modeling. Self-Modulating QFWP improves this framework by using input-dependent gates for both new fast-weight updates and the accumulated fast-weight state, but its unbounded old-state multiplier can diverge in long-sequence regimes. We propose a bounded old-state modulation rule that applies a sign-preserving tanh gate only to the recurrent memory branch while leaving the additive update and new-update modulation unchanged. We evaluate standard QFWP, full Self-Modulating QFWP, Only-New, and Only-Old variants on two CUDA-Q quantum-dynamics forecasting tasks and on Milan SMS telecommunication activity prediction. The quantum-dynamics results show that old-state modulation is the most consistent source of improvement over Standard QFWP, and that bounding the old-state gate removes long-sequence divergence while improving aggregate robustness. On Milan SMS forecasting, the original unbounded Self-Modulating QFWP converges across the tested grid and shows its clearest gains at longer input windows, with behavior close to the Only-Old ablation. These findings identify accumulated-memory modulation as the key mechanism of Self-Modulating QFWP and bounded old-state gating as a targeted stabilization strategy.

Related papers

• Complementary Matrix-Gated QKAN Fast-Weight Programmers for Quantum Dynamics Forecasting [38.586966822977686]
  Gated fast-weight programmers (FWPs) based on quantum-inspired Kolmogorov-Arnold networks (QKANs)<n>We introduce Self-Modulating QKAN-based FWPs with low-rank-wise modulation.
  arXiv  Detail & Related papers  (2026-07-30T09:52:22Z)
• Self-Modulating Quantum Fast-Weight Programmers for Efficient Adaptive Sequential Learning [36.260056870107874]
  We propose Self-Modulating Quantum Fast Weight Programmers (QFWP)<n>Self-Modulating QFWP introduces adaptive modulation over both newly generated fast-weight updates and historical fast-weight memory.<n>Results show that the proposed mechanism improves convergence stability and prediction performance across varying model settings.
  arXiv  Detail & Related papers  (2026-06-22T10:21:03Z)
• QLAM: A Quantum Long-Attention Memory Approach to Long-Sequence Token Modeling [14.229084182282607]
  We introduce one of the first studies to leverage the superposition property of quantum systems to enhance state-based sequence modeling.<n>QLAM represents the hidden state as a quantum state whose amplitudes encode a superposition of historical information.<n>We evaluate QLAM on sequential variants of standard image classification benchmarks, including sMNIST, sFashion-MNIST, and sCIFAR-10.
  arXiv  Detail & Related papers  (2026-05-13T17:56:20Z)
• Gated QKAN-FWP: Scalable Quantum-inspired Sequence Learning [38.502127166117674]
  We propose gated QKAN-FWP, a fast-weight framework that integrates FWP with Quantum-inspired Kolmogorov-Arnold Network (QKAN)<n>We use single-qubit data re-uploading circuits as learnable nonlinear activation, known as DatA Re-Uploading ActivatioN (DARUAN)<n>We evaluate the framework across time-series benchmarks, MiniGrid reinforcement learning, and highlight real-world solar cycle forecasting as our main practical result.
  arXiv  Detail & Related papers  (2026-05-07T13:04:09Z)
• PAMod: Modeling Cyclical Shifts via Phase-Amplitude Modulation for Non-stationary Time Series Forecasting [59.88916926133985]
  We propose PAMod, a framework that models cyclical distribution shifts via Phase-Amplitude Modulation in the normalized feature space.<n>We show that PAMod achieves state-of-the-art performance with fewer computational resources.<n>Our modulation mechanism, as a novel plug-and-play technique, can improve existing time-series forecasting methods with simple integration.
  arXiv  Detail & Related papers  (2026-05-01T07:09:23Z)
• 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)
• EntroPE: Entropy-Guided Dynamic Patch Encoder for Time Series Forecasting [50.794700596484894]
  We propose EntroPE (Entropy-Guided Dynamic Patch), a novel, temporally informed framework that dynamically detects transition points via conditional entropy.<n>This preserves temporal structure while retaining the computational benefits of patching.<n> Experiments across long-term forecasting benchmarks demonstrate that EntroPE improves both accuracy and efficiency.
  arXiv  Detail & Related papers  (2025-09-30T12:09:56Z)
• Quantum-Optimized Selective State Space Model for Efficient Time Series Prediction [39.146761527401424]
  We propose a hybrid quantum-optimized approach that integrates state space dynamics with a variational quantum gate.<n>We empirically validate Q-SSM on three widely used benchmarks, i.e., ETT, Traffic, and Exchange Rate.<n>Results show that Q-SSM consistently improves over strong baselines.
  arXiv  Detail & Related papers  (2025-08-29T22:00:48Z)
• Towards Continual Learning Desiderata via HSIC-Bottleneck Orthogonalization and Equiangular Embedding [55.107555305760954]
  We propose a conceptually simple yet effective method that attributes forgetting to layer-wise parameter overwriting and the resulting decision boundary distortion. Our method achieves competitive accuracy performance, even with absolute superiority of zero exemplar buffer and 1.02x the base model.
  arXiv  Detail & Related papers  (2024-01-17T09:01:29Z)
• Adaptive Variational Quantum Dynamics Simulations [3.629716738568079]
  We propose a general-purpose, self-adaptive approach to construct variational wavefunction ans"atze for highly accurate quantum dynamics simulations. We apply this approach to the integrable Lieb-Schultz-Mattis spin chain and the nonintegrable mixed-field Ising model. We envision that a wide range of dynamical simulations of quantum many-body systems on near-term quantum computing devices will be made possible through the AVQDS framework.
  arXiv  Detail & Related papers  (2020-11-01T20:21:57Z)

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.