Complementary Matrix-Gated QKAN Fast-Weight Programmers for Quantum Dynamics Forecasting

• URL: http://arxiv.org/abs/2607.27945v1
• Date: Thu, 30 Jul 2026 09:52:22 GMT
• Title: Complementary Matrix-Gated QKAN Fast-Weight Programmers for Quantum Dynamics Forecasting
• Abstract summary: 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.
• Score: 38.586966822977686
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Sequence models must decide what to write into memory and what to retain. In quantum and quantum-inspired sequence learning, nonlinear recurrent updates often require repeated circuit evaluations and sequential backpropagation through time, making long contexts costly. Gated fast-weight programmers (FWPs) based on quantum-inspired Kolmogorov-Arnold networks (QKANs) alleviate this bottleneck by storing context in time-varying fast parameters. However, their scalar gate applies one retention-write balance to every fast-state coordinate, forcing all parameters to share a memory timescale. We introduce Self-Modulating QKAN-based FWPs, which replace this broadcast gate with low-rank-generated element-wise modulation of the new-proposal branch, a bounded old-state branch, or both. We further propose Complementary Matrix Gating (CMG), which uses one sigmoid matrix gate to retain the old state and its complement to write the new proposal. CMG provides coordinate-wise memory control while preserving the bounded convex update and affine prefix-scan structure of scalar gating, at the modulation-head cost of a single-branch rule. We compare four self-modulating rules with scalar gating across four FWP architectures combining classical and QKAN-based slow and fast programmers. Across seven single-step forecasting benchmarks and five sequence lengths, CMG gives the most consistent improvements for architectures whose fast programmer incorporates a QKAN-based module. In direct multi-step forecasting of Jaynes-Cummings and transmon-resonator dynamics simulated with CUDA-Q Dynamics, CMG models maintain mean-squared errors on the order of 0.001 or lower across forecasting horizons of 4, 8, and 16 steps, while improving on their scalar-gated counterparts by at least 91.2%. These results establish coordinate-wise complementary modulation as a stable and effective update for QKAN-based FWPs.

Related papers

• Stable Self-Modulating Quantum Fast-Weight Programmers with Bounded Memory Gates [36.26005687010788]
  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.
  arXiv  Detail & Related papers  (2026-07-02T16:06:04Z)
• Parameter-Efficient Quantum-Inspired Fast Weight Programmers for Traffic-Matrix Forecasting [10.494232787136452]
  This paper investigates whether compact quantum-inspired recurrent models can provide effective TM forecasts without relying on dedicated graph, transformer, or diffusion modules.<n>We adapt gated quantum-inspired Kolmogorov-Arnold network fast-weight programmers (QKAN-FWPs) to direct Abilene TM forecasting.<n>We benchmark three QKAN placement variants against a matched-size long short-term memory (LSTM) network, a larger LSTM, and a classical gated fast-weight programmer under a shared fixed-budget training protocol.
  arXiv  Detail & Related papers  (2026-06-26T08:02:27Z)
• Perceive, Route and Modulate: Dynamic Pattern Recalibration for Time Series Forecasting [68.53528085362642]
  Current deep forecasting models rely on fixed weight matrices applied uniformly to all temporal tokens.<n>We introduce Dynamic Pattern Recalibration, a backbone-agnostic mechanism that resolves this via token-level recalibration.<n>DPRNet achieves competitive performance across 12 benchmarks, validating dynamic recalibration against macroscopic parameter scaling.
  arXiv  Detail & Related papers  (2026-05-07T14:12:47Z)
• 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)
• LiQSS: Post-Transformer Linear Quantum-Inspired State-Space Tensor Networks for Real-Time 6G [85.58816960936069]
  Proactive and agentic control in Sixth-Generation (6G) Open Radio Access Networks (O-RAN) requires control-grade prediction under stringent Near-Time (Near-RT) latency and computational constraints.<n>This paper investigates a post-Transformer paradigm for efficient radio telemetry forecasting.<n>We propose a quantum-inspired state-space tensor network that replaces self-attention with stable structured state-space dynamics kernels.
  arXiv  Detail & Related papers  (2026-01-18T12:08:38Z)
• 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)
• Sequential-Parallel Duality in Prefix Scannable Models [68.39855814099997]
  Recent developments have given rise to various models, such as Gated Linear Attention (GLA) and Mamba.<n>This raises a natural question: can we characterize the full class of neural sequence models that support near-constant-time parallel evaluation and linear-time, constant-space sequential inference?
  arXiv  Detail & Related papers  (2025-06-12T17:32:02Z)
• Efficient Sparse State Preparation via Quantum Walks [4.864856930458624]
  We develop an algorithm that converts single-edge and self-loop dynamic CTQWs to the gate model of computation.<n>We use this mapping to introduce an efficient quantum state preparation framework based on dynamic CTQWs.
  arXiv  Detail & Related papers  (2024-05-30T17:28:23Z)
• Squeezeformer: An Efficient Transformer for Automatic Speech Recognition [99.349598600887]
  Conformer is the de facto backbone model for various downstream speech tasks based on its hybrid attention-convolution architecture. We propose the Squeezeformer model, which consistently outperforms the state-of-the-art ASR models under the same training schemes.
  arXiv  Detail & Related papers  (2022-06-02T06:06:29Z)

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.