Quantum Dynamic Time Warping for Multivariate Time Series Classification

• URL: http://arxiv.org/abs/2606.27815v1
• Date: Fri, 26 Jun 2026 07:58:37 GMT
• Title: Quantum Dynamic Time Warping for Multivariate Time Series Classification
• Abstract summary: We propose a hybrid Quantum Dynamic Time Warping architecture, replacing the classical distance metric with the parameterized geometry of a quantum Hilbert space.<n>We demonstrate this architecture allows untrained quantum kernels to act as highly expressive baselines, while parameterized training effectively untangles deeply overlapping hyper-dimensional data.
• Score: 41.99844472131922
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Dynamic Time Warping (DTW) is a cornerstone for time series classification, but its reliance on Euclidean distances fails to capture latent cross-channel correlations in complex multivariate data. We propose a hybrid Quantum Dynamic Time Warping (qDTW) architecture, replacing the classical distance metric with the parameterized geometry of a quantum Hilbert space. Through structural ablation on benchmarks up to $C=8$ spatial dimensions, we establish fundamental topological rules for quantum sequence alignment. We introduce a Unified Pre-Embedding Adjoint Ansatz that decouples trainable entanglement from classical data, eliminating the severe phase-scrambling and information bottlenecks inherent to traditional measurements. We demonstrate this decoupled architecture allows untrained quantum kernels to act as highly expressive baselines, while parameterized training effectively untangles deeply overlapping hyper-dimensional data. Furthermore, we identify a strict spatial-temporal expressivity tradeoff: temporal depth (data re-uploading) is necessary for dimensionally restricted univariate circuits, but applying it to wide multi-qubit registers triggers chaotic frequency-spectrum explosions and representation collapse. By navigating these topological hazards, our multivariate quantum architecture outperforms classical baselines, setting a new standard for integrating parameterized quantum circuits with dynamic programming

Related papers

• Hybrid Quantum Temporal Convolutional Networks [30.67106331673231]
  HQTCN combines classical temporal windowing with a quantum convolutional neural network core.<n> evaluated on synthetic NARMA sequences and high-dimensional EEG time-series.
  arXiv  Detail & Related papers  (2026-02-27T01:06:51Z)
• Forecasting as Rendering: A 2D Gaussian Splatting Framework for Time Series Forecasting [79.37674445572462]
  Time series forecasting (TSF) remains a challenging problem due to the intricate entanglement of intraperiod-fluctuations and interperiod-trends.<n>Treating reshaped tensors as static images results in a topological mismatch.<n> relying on uniform fixed-size representations allocates modeling capacity inefficiently.<n>TimeGS is a novel framework that fundamentally shifts the forecasting paradigm from regression to 2D generative rendering.
  arXiv  Detail & Related papers  (2026-02-10T14:13:36Z)
• 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)
• Implementing a Universal Set of Geometric Quantum Gates through Dressed-State assisted STA [39.27725073249277]
  We analyze the implementation of single-qubit gates in a two-level system driven by a microwave field.<n>We show how the dynamical phase can be canceled to obtain purely geometric operations.<n>We extend the protocol to construct non two-qubit gates, highlighting its feasibility for scalable quantum information processing.
  arXiv  Detail & Related papers  (2025-09-10T16:14:34Z)
• Forecasting Low-Dimensional Turbulence via Multi-Dimensional Hybrid Quantum Reservoir Computing [0.0]
  We introduce a hybrid quantum-classical reservoir architecture capable of handling multivariate time series through quantum evolution combined with classical memory enhancement.<n>We apply this framework to two paradigmatic models of chaotic behavior in fluid dynamics, where multiscale dynamics and nonlinearities play a dominant role.<n>The robustness observed and reliable performances for both dynamical systems suggest that this hybrid quantum approach offers a flexible platform for modelling complex nonlinear time series.
  arXiv  Detail & Related papers  (2025-09-04T08:37:48Z)
• Quantum-Optimized Selective State Space Model for Efficient Time Series Prediction [39.146761527401424]
  We propose a hybrid quantum-optimized approach that integrates state space dynamics with a variational quantum gate.<n>We empirically validate Q-SSM on three widely used benchmarks, i.e., ETT, Traffic, and Exchange Rate.<n>Results show that Q-SSM consistently improves over strong baselines.
  arXiv  Detail & Related papers  (2025-08-29T22:00:48Z)
• Quantum neural ordinary and partial differential equations [38.77776626953413]
  We present a unified framework that brings the continuous-time formalism of classical neural ODEs/PDEs into quantum machine learning and quantum control.<n>We define QNODEs as the evolution of finite-dimensional quantum systems, and QNPDEs as infinite-dimensional (continuous-variable) counterparts.
  arXiv  Detail & Related papers  (2025-08-24T18:43:44Z)
• Quantum Krylov Subspace Diagonalization via Time Reversal Symmetries [0.8983000676504389]
  Krylov quantum diagonalization methods have emerged as a promising use case for quantum computers.<n>Existing implementations rely on controlled operations, which pose challenges to near-term quantum hardware.<n>We introduce a novel protocol, termed Krylov Time Reversal (KTR), that circumvents these bottlenecks by leveraging time-reversal symmetry in Hamiltonian evolution.
  arXiv  Detail & Related papers  (2025-07-30T10:35:36Z)
• Constructive interference at the edge of quantum ergodic dynamics [116.94795372054381]
  We characterize ergodic dynamics using the second-order out-of-time-order correlators, OTOC$(2)$.<n>In contrast to dynamics without time reversal, OTOC$(2)$ are observed to remain sensitive to the underlying dynamics at long time scales.
  arXiv  Detail & Related papers  (2025-06-11T21:29:23Z)
• Quantum-Enhanced Channel Mixing in RWKV Models for Time Series Forecasting [0.0]
  Recent advancements in neural sequence modeling have led to architectures such as RWKV, which combine recurrent-style time mixing with feedforward channel mixing to enable efficient long-context processing.<n>In this work, we propose QuantumRWKV, a hybrid quantum-Piece extension of the RWKV model, where the standard feedforward network (FFN) is partially replaced by a variational quantum circuit (VQC)<n>The quantum component is designed to enhance nonlinear representational capacity while preserving end-to-end differentiability via the PennyLane framework.
  arXiv  Detail & Related papers  (2025-05-18T02:19:30Z)
• Efficient Learning for Linear Properties of Bounded-Gate Quantum Circuits [62.46800898243033]
  Recent progress in quantum learning theory prompts a question: can linear properties of a large-qubit circuit be efficiently learned from measurement data generated by varying classical inputs?<n>We prove that the sample complexity scaling linearly in $d$ is required to achieve a small prediction error, while the corresponding computational complexity may scale exponentially in d.<n>We propose a kernel-based method leveraging classical shadows and truncated trigonometric expansions, enabling a controllable trade-off between prediction accuracy and computational overhead.
  arXiv  Detail & Related papers  (2024-08-22T08:21:28Z)
• The Quantum Path Kernel: a Generalized Quantum Neural Tangent Kernel for Deep Quantum Machine Learning [52.77024349608834]
  Building a quantum analog of classical deep neural networks represents a fundamental challenge in quantum computing. Key issue is how to address the inherent non-linearity of classical deep learning. We introduce the Quantum Path Kernel, a formulation of quantum machine learning capable of replicating those aspects of deep machine learning.
  arXiv  Detail & Related papers  (2022-12-22T16:06:24Z)
• Out-of-equilibrium dynamics arising from slow round-trip variations of Hamiltonian parameters across quantum and classical critical points [0.0]
  We address the out-of-equilibrium dynamics of many-body systems subject to slow time-dependent round-trip protocols across quantum and classical (thermal) phase transitions. We consider protocols where one relevant parameter w is slowly changed across its critical point wc = 0, linearly in time with a large time scale ts.
  arXiv  Detail & Related papers  (2022-05-17T13:27:32Z)

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.