Pith. sign in

REVIEW 9 cited by

Quantum Variational Activation Functions Empower Kolmogorov-Arnold Networks

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2509.14026 v2 pith:3SBCFID2 submitted 2025-09-17 quant-ph cs.LG

Quantum Variational Activation Functions Empower Kolmogorov-Arnold Networks

classification quant-ph cs.LG
keywords quantumactivationefficiencycircuitsdaruanfunctionskolmogorov-arnoldparameter
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Variational quantum circuits (VQCs) are central to quantum machine learning, while recent progress in Kolmogorov-Arnold networks (KANs) highlights the power of learnable activation functions. We unify these directions by introducing the quantum variational activation function (QVAF), a general framework in which parameterized quantum circuits serve as learnable activation functions; in this work we study an efficient single-qubit instantiation called DatA Re-Uploading ActivatioN (DARUAN). We show that DARUAN with trainable data-preprocessing weights can realize an exponentially growing accessible frequency support with the number of re-uploading repetitions; for an explicit geometric choice of these weights, this gives a capacity-level exponential parameter reduction relative to independently parameterized Fourier activations. Embedding DARUAN into KAN yields the quantum-inspired Kolmogorov-Arnold Network (QKAN), which retains the interpretability of the KAN architecture while improving parameter efficiency, expressivity, and generalization. We further introduce layer extension and the hybrid QKAN (HQKAN) architecture to improve scalability and computational efficiency, enabling QKAN modules to act as compact replacements for multi-layer perceptrons (MLPs) in large-scale models. We provide theoretical analysis and extensive experiments on function regression, image classification, and autoregressive generative language modeling, demonstrating the efficiency and scalability of QKANs. Because the single-qubit circuits are efficiently simulable on classical quantum simulators, QKANs have quantum-inspired advantage in parameter efficiency and training stability; DARUANs and QKANs serve as present-day validation of the QVAF concept, and the trained DARUANs are directly executable and feasible on current noisy intermediate-scale quantum (NISQ) hardware for inference validation.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Gated QKAN-FWP: Scalable Quantum-inspired Sequence Learning

    cs.LG 2026-05 unverdicted novelty 7.0

    Gated QKAN-FWP combines fast weight programming with quantum-inspired Kolmogorov-Arnold networks via single-qubit DARUAN activations and gated updates to deliver a 12.5k-parameter model that outperforms larger classic...

  2. Generative Quantum-inspired Kolmogorov-Arnold Eigensolver

    quant-ph 2026-05 unverdicted novelty 7.0

    GQKAE uses quantum-inspired Kolmogorov-Arnold networks to reduce parameters by 66% in generative quantum eigensolvers while achieving chemical accuracy on H4, N2, LiH, and other molecules.

  3. Quantum Kolmogorov--Arnold representation theorem for continuous unitary-valued maps

    quant-ph 2026-07 accept novelty 6.5

    Continuous unitary maps near the identity admit exact Kolmogorov-Arnold decompositions as exp of summed univariate anti-Hermitian fields or as products of univariate matrix exponentials; the results fail globally on U(n).

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

    quant-ph 2026-07 conditional novelty 5.0

    Complementary Matrix Gating gives QKAN fast-weight programmers coordinate-wise retain/write control and cuts multi-step quantum-dynamics forecast MSE by at least 91.2% versus scalar gates.

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

    quant-ph 2026-07 unverdicted novelty 5.0

    Introduces bounded old-state modulation via tanh gate to stabilize self-modulating QFWPs, with evaluations showing reduced divergence and improved robustness on quantum dynamics and SMS tasks.

  6. Recursive QLSTM with Dynamic Variational Quantum Circuit Adaptation

    quant-ph 2026-06 unverdicted novelty 4.0

    The paper introduces Recursive QLSTM via metacore recursion, numerically tests variants on sequence lengths, and offers theoretical arguments for better temporal propagation.

  7. Parameter-Efficient Quantum-Inspired Fast Weight Programmers for Traffic-Matrix Forecasting

    quant-ph 2026-06 unverdicted novelty 3.0

    Gated QKAN fast-weight programmer achieves lowest pooled RMSE on Abilene TM forecasting while using 22.4% of a larger LSTM's parameters and outperforming classical G-FWP.

  8. Self-Modulating Quantum Fast-Weight Programmers for Efficient Adaptive Sequential Learning

    quant-ph 2026-06 unverdicted novelty 3.0

    Self-Modulating QFWP adds adaptive modulation to quantum fast-weight updates and memory to improve stability and performance on sequential learning tasks.

  9. A Practitioner's Guide to Kolmogorov-Arnold Networks

    cs.LG 2025-10 accept novelty 3.0

    A systematic review of Kolmogorov-Arnold Networks that maps their relation to Kolmogorov superposition theory, MLPs, and kernels, examines basis-function design choices, summarizes performance advances, and supplies a...