QKAN: quantum Kolmogorov-Arnold networks with applications in machine learning and multivariate state preparation

Abstract

We introduce quantum Kolmogorov-Arnold networks (QKAN), a quantum algorithmic framework inspired by the recently proposed Kolmogorov-Arnold Networks (KAN). QKAN inherits the compositional structure of KAN and is based on block-encodings, constructed recursively from a single layer using quantum singular value transformation. We demonstrate the algorithmic utility of QKAN in two applications. First, we introduce and analyze QKAN as a quantum learning model, treating the eigenvalues of block-encoded matrices as neurons and applying parametrized activation functions on the edges of the network. We show that QKAN is a wide-and-shallow neural architecture, where shallow depth is compensated by exponentially wide layers whenever efficient block-encodings of inputs are available. We further discuss how to parametrize and train QKAN using parametrized quantum circuits and quantum linear algebra subroutines. Second, we demonstrate that QKAN can serve as a multivariate quantum state-preparation protocol for functions with shallow compositional structure. We demonstrate this by efficiently preparing a multivariate Gaussian quantum state using a two-layer QKAN. Looking forward, we anticipate that QKAN's compositional and modular design will enable new applications in quantum machine learning and quantum state preparation.

19 main-text pages, 34 pages in total, 10 figures

References in corpus (48)

• Quantum Machine Learning
• Variational Quantum Algorithms
• Supervised learning with quantum enhanced feature spaces
• Quantum support vector machine for big data classification
• Quantum machine learning in feature Hilbert spaces
• Quantum Circuit Learning
• Machine learning phases of matter
• Quantum Amplitude Amplification and Estimation
• Parameterized quantum circuits as machine learning models
• Evaluating analytic gradients on quantum hardware
• Circuit-centric quantum classifiers
• Hamiltonian Simulation by Qubitization
• Optimal Hamiltonian Simulation by Quantum Signal Processing
• Simulating Hamiltonian dynamics with a truncated Taylor series
• The effect of data encoding on the expressive power of variational quantum machine learning models
• Efficient Learning for Deep Quantum Neural Networks
• Connecting ansatz expressibility to gradient magnitudes and barren plateaus
• Quantum singular value transformation and beyond: exponential improvements for quantum matrix arithmetics
• Quantum Natural Gradient
• Quantum-state preparation with universal gate decompositions
• The Expressive Power of Parameterized Quantum Circuits
• Creating superpositions that correspond to efficiently integrable probability distributions
• Fixed-point quantum search with an optimal number of queries
• Kolmogorov Arnold Informed neural network: A physics-informed deep learning framework for solving forward and inverse problems based on Kolmogorov Arnold Networks
• Quantum Hopfield neural network
• Quantum State Preparation with Optimal Circuit Depth: Implementations and Applications
• Generalization in Quantum Machine Learning: a Quantum Information Perspective
• Efficient phase-factor evaluation in quantum signal processing
• Black-box quantum state preparation without arithmetic
• The power of block-encoded matrix powers: improved regression techniques via faster Hamiltonian simulation
• Quantum natural gradient generalised to noisy and non-unitary circuits
• KANQAS: Kolmogorov-Arnold Network for Quantum Architecture Search
• Quantum algorithms: A survey of applications and end-to-end complexities
• Quantum Algorithm for Fidelity Estimation
• Efficient quantum amplitude encoding of polynomial functions
• The Efficient Preparation of Normal Distributions in Quantum Registers
• On the Interpretability of Quantum Neural Networks
• Wavefunction preparation and resampling using a quantum computer
• New Quantum Algorithms for Computing Quantum Entropies and Distances
• Amplitude Estimation from Quantum Signal Processing
• Nearly-optimal state preparation for quantum simulations of lattice gauge theories
• Improved Quantum Algorithms for Fidelity Estimation
• Quantum state preparation for multivariate functions
• The State Preparation of Multivariate Normal Distributions using Tree Tensor Network
• Exponential Quantum Advantage for Pathfinding in Regular Sunflower Graphs
• Quantum Transformer: Accelerating model inference via quantum linear algebra
• The Quantum Esscher Transform
• A simpler Gaussian state-preparation