Continual Quantum Architecture Search with Tensor-Train Encoding: Theory and Applications to Signal Processing

2026-01-10

AI Summary

This work proposes CL-QAS, a novel framework addressing the high cost of amplitude encoding in variational quantum circuits and catastrophic forgetting in continual learning. CL-QAS introduces Tensor-Train encoding into quantum architecture search for the first time, enabling efficient compression of high-dimensional signals into low-rank quantum features. It employs a dual-loop optimization strategy to decouple parameter updates from architecture search and incorporates elastic weight consolidation regularization to ensure stability across task sequences. Theoretical analysis demonstrates that the framework offers controllable expressivity, sample-efficient generalization, smooth convergence without barren plateaus, and robustness to quantum noise. Empirical evaluations on ECG classification and financial time-series prediction tasks show significant improvements in accuracy, F1 score, and reward, along with strong forward and backward transfer capabilities and consistent performance under depolarizing and readout noise.

Technology Category

• Machine Learning: Quantum Machine Learning
• Search and Optimization: Learning to Search
• Computer Vision: Learning & Optimization for CV

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

We introduce CL-QAS, a continual quantum architecture search framework that mitigates the challenges of costly amplitude encoding and catastrophic forgetting in variational quantum circuits. The method uses Tensor-Train encoding to efficiently compress high-dimensional stochastic signals into low-rank quantum feature representations. A bi-loop learning strategy separates circuit parameter optimization from architecture exploration, while an Elastic Weight Consolidation regularization ensures stability across sequential tasks. We derive theoretical upper bounds on approximation, generalization, and robustness under quantum noise, demonstrating that CL-QAS achieves controllable expressivity, sample-efficient generalization, and smooth convergence without barren plateaus. Empirical evaluations on electrocardiogram (ECG)-based signal classification and financial time-series forecasting confirm substantial improvements in accuracy, balanced accuracy, F1 score, and reward. CL-QAS maintains strong forward and backward transfer and exhibits bounded degradation under depolarizing and readout noise, highlighting its potential for adaptive, noise-resilient quantum learning on near-term devices.

Problem

• continual learning
• quantum architecture search
• amplitude encoding
• catastrophic forgetting
• quantum noise

Innovation

• Continual Quantum Architecture Search
• Tensor-Train Encoding
• Elastic Weight Consolidation
• Barren Plateau Mitigation
• Noise-Resilient Quantum Learning