Investigating the Lottery Ticket Hypothesis for Variational Quantum Circuits

2025-09-14

AI Summary

Variational quantum circuits (VQCs) suffer from barren plateaus—exponentially vanishing gradients—that impede optimization. Method: This work introduces the Lottery Ticket Hypothesis (LTH) to VQCs for the first time, proposing an iterative pruning and mask-learning framework to identify quantum subnetworks—“winning tickets”—without training. Contribution/Results: We theoretically and empirically validate the weak LTH in VQCs and, for the first time, demonstrate the strong LTH: a pruned subnetwork retaining only 45% of parameters achieves 100% classification accuracy; the optimal compression retains just 26.0% of parameters while preserving full original performance. This establishes a novel paradigm for efficient initialization, model compression, and optimization of quantum neural networks, opening a new pathway toward parameter-efficient quantum machine learning.

Technology Category

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

Application Category

• 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
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Quantum computing is an emerging field in computer science that has seen considerable progress in recent years, especially in machine learning. By harnessing the principles of quantum physics, it can surpass the limitations of classical algorithms. However, variational quantum circuits (VQCs), which rely on adjustable parameters, often face the barren plateau phenomenon, hindering optimization. The Lottery Ticket Hypothesis (LTH) is a recent concept in classical machine learning that has led to notable improvements in parameter efficiency for neural networks. It states that within a large network, a smaller, more efficient subnetwork, or ''winning ticket,'' can achieve comparable performance, potentially circumventing plateau challenges. In this work, we investigate whether this idea can apply to VQCs. We show that the weak LTH holds for VQCs, revealing winning tickets that retain just 26.0% of the original parameters. For the strong LTH, where a pruning mask is learned without any training, we discovered a winning ticket in a binary VQC, achieving 100% accuracy with only 45% of the weights. These findings indicate that LTH may mitigate barren plateaus by reducing parameter counts while preserving performance, thus enhancing the efficiency of VQCs in quantum machine learning tasks.

Problem

• Investigating Lottery Ticket Hypothesis for variational quantum circuits
• Addressing barren plateau problem in quantum circuit optimization
• Finding efficient subnetworks to reduce parameter counts

Innovation

• Applying Lottery Ticket Hypothesis to quantum circuits
• Pruning variational quantum circuits to reduce parameters
• Mitigating barren plateaus through parameter efficiency