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

Hugging Face Daily Papers Papers
quantum-dynamics sequence-modeling kolmogorov-arnold-networks fast-weight-programmers matrix-gating forecasting

Summary

This paper introduces Complementary Matrix Gating (CMG) for QKAN-based fast-weight programmers, enabling coordinate-wise memory control for quantum dynamics forecasting. The method shows consistent improvements and low mean-squared errors on quantum simulation benchmarks.

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.
Original Article
View Cached Full Text

Cached at: 08/10/26, 10:17 PM

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

Source: https://huggingface.co/papers/2607.27945 Authors:

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

Sequencemodelsmustdecidewhattowriteintomemoryandwhattoretain.Inquantumandquantum-inspiredsequencelearning,nonlinearrecurrentupdatesoftenrequirerepeatedcircuitevaluationsandsequentialbackpropagationthroughtime,makinglongcontextscostly.Gatedfast-weightprogrammers(FWPs)basedonquantum-inspiredKolmogorov-Arnoldnetworks(QKANs)alleviatethisbottleneckbystoringcontextintime-varyingfastparameters.However,theirscalargateappliesoneretention-writebalancetoeveryfast-statecoordinate,forcingallparameterstoshareamemorytimescale.WeintroduceSelf-ModulatingQKAN-basedFWPs,whichreplacethisbroadcastgatewithlow-rank-generatedelement-wisemodulationofthenew-proposalbranch,aboundedold-statebranch,orboth.WefurtherproposeComplementaryMatrixGating(CMG),whichusesonesigmoidmatrixgatetoretaintheoldstateanditscomplementtowritethenewproposal.CMGprovidescoordinate-wisememorycontrolwhilepreservingtheboundedconvexupdateandaffineprefix-scanstructureofscalargating,atthemodulation-headcostofasingle-branchrule.Wecomparefourself-modulatingruleswithscalargatingacrossfourFWParchitecturescombiningclassicalandQKAN-basedslowandfastprogrammers.Acrosssevensingle-stepforecastingbenchmarksandfivesequencelengths,CMGgivesthemostconsistentimprovementsforarchitectureswhosefastprogrammerincorporatesaQKAN-basedmodule.Indirectmulti-stepforecastingofJaynes-Cummingsandtransmon-resonatordynamicssimulatedwithCUDA-QDynamics,CMGmodelsmaintainmean-squarederrorsontheorderof0.001orloweracrossforecastinghorizonsof4,8,and16steps,whileimprovingontheirscalar-gatedcounterpartsbyatleast91.2%.Theseresultsestablishcoordinate-wisecomplementarymodulationasastableandeffectiveupdateforQKAN-basedFWPs.

View arXiv pageView PDFAdd to collection

Get this paper in your agent:

hf papers read 2607\.27945

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2607.27945 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2607.27945 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2607.27945 in a Space README.md to link it from this page.

Collections including this paper1

Similar Articles

Gated QKAN-FWP: Scalable Quantum-inspired Sequence Learning

Hugging Face Daily Papers

# Paper page - Gated QKAN-FWP: Scalable Quantum-inspired Sequence Learning Source: [https://huggingface.co/papers/2605.06734](https://huggingface.co/papers/2605.06734) Authors: , , , , , , , , , , , , , , , , , ## Abstract Quantum\-inspired fast\-weight programming framework using single\-qubit circuits achieves superior forecasting performance with reduced parameters compared to classical recurrent models while maintaining NISQ device compatibility\. [Fast Weight Programmers](https://huggingfac

Generative Quantum-inspired Kolmogorov-Arnold Eigensolver

Hugging Face Daily Papers

This paper introduces the Generative Quantum-inspired Kolmogorov-Arnold Eigensolver (GQKAE), a parameter-efficient architecture that replaces traditional neural components with Kolmogorov-Arnold modules to significantly reduce memory usage and improve convergence in quantum chemistry simulations.