Paper page - Gated QKAN-FWP: Scalable Quantum-inspired Sequence Learning

Source: 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(FWPs) encode temporal dependencies through dynamically updated parameters rather than recurrent hidden states.Quantum FWPs(QFWPs) extend this idea withvariational quantum circuits(VQCs), but existing implementations rely on multi-qubit architectures that are difficult to scale on noisy intermediate-scale quantum (NISQ) devices and expensive to simulate classically. We propose gated QKAN-FWP, a fast-weight framework that integrates FWP withQuantum-inspired Kolmogorov-Arnold Network(QKAN) using single-qubitdata re-uploading circuitsas learnable nonlinear activation, known as DatA Re-Uploading ActivatioN (DARUAN). We further introduce ascalar-gated fast-weight update rulethat stabilizes parameter evolution, supported by a theoretical analysis of itsadaptive memory kernel,geometric boundedness, andparallelizable gradient paths. We evaluate the framework acrosstime-series benchmarks,MiniGridreinforcement learning, and highlight real-worldsolar cycle forecastingas our main practical result. In the long-horizon setting with 528-month input window and 132-month forecast horizon, our 12.5k-parameter model achieves lowerscaled Mean Square Error(MSE), peak amplitude error, and peak timing error than a suite of classical recurrent baselines with up to 13x more parameters, including Long Short-Term Memory (LSTM) networks (25.9k-89.1k parameters),WaveNet-LSTM(167k), Vanilla recurrent neural network (11.5k), and aModified Echo State Network(132k). To validate NISQ compatibility, we further deploy the trained fast programmer onIonQandIBM Quantumprocessors, recovering forecasting accuracy within 0.1% relative MSE of the noiseless simulator at 1024 shots. These results position gated QKAN-FWP as a scalable, parameter-efficient, and NISQ-compatible approach to quantum-inspired sequence modeling.

View arXiv pageView PDFAdd to collection

Get this paper in your agent:

hf papers read 2605\.06734

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/2605.06734 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2605.06734 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2605.06734 in a Space README.md to link it from this page.

Collections including this paper1