Quantum Curriculum Learning

2024-07-02

arXiv.org

AI Summary

To address the low training efficiency, poor generalization, and weak noise robustness of hierarchical quantum data on NISQ devices, this paper proposes the Quantum Curriculum Learning (Q-CurL) framework. Q-CurL introduces— for the first time—a curriculum design principle based on quantum state density ratios and a dynamic information-prioritization scheduling mechanism, enabling data-driven learning from simple to complex tasks. Integrating quantum machine learning, curriculum learning, and quantum state density analysis, the method significantly accelerates convergence and improves generalization in unit learning tasks, while enhancing noise robustness and sample efficiency in quantum phase identification. Experiments are conducted on representative condensed-matter physics and quantum chemistry benchmarks, demonstrating scalability and strong robustness under hardware resource constraints. Q-CurL establishes a novel, resource-efficient paradigm for quantum learning on near-term devices.

Technology Category

• Machine Learning: Quantum Machine Learning
• Search and Optimization: Learning to Search
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Quantum machine learning (QML) requires significant quantum resources to address practical real-world problems. When the underlying quantum information exhibits hierarchical structures in the data, limitations persist in training complexity and generalization. Research should prioritize both the efficient design of quantum architectures and the development of learning strategies to optimize resource usage. We propose a framework called quantum curriculum learning (Q-CurL) for quantum data, where the curriculum introduces simpler tasks or data to the learning model before progressing to more challenging ones. Q-CurL exhibits robustness to noise and data limitations, which is particularly relevant for current and near-term noisy intermediate-scale quantum devices. We achieve this through a curriculum design based on quantum data density ratios and a dynamic learning schedule that prioritizes the most informative quantum data. Empirical evidence shows that Q-CurL significantly enhances training convergence and generalization for unitary learning and improves the robustness of quantum phase recognition tasks. Q-CurL is effective with broad physical learning applications in condensed matter physics and quantum chemistry.

Problem

• Efficient quantum resource usage in machine learning
• Training complexity in hierarchical quantum data
• Robustness to noise in quantum devices

Innovation

• Quantum curriculum learning for hierarchical data
• Dynamic schedule prioritizing informative quantum data
• Robust to noise and data limitations