Neural Guided Sampling for Quantum Circuit Optimization

2025-10-14

AI Summary

Compiling quantum circuits onto hardware with restricted topology often incurs excessive circuit depth due to limited native gate sets, thereby exacerbating decoherence errors. To address this, we propose a 2D neural-guided sampling method that maps quantum circuits onto a two-dimensional structural representation and trains a neural network to predict gate groups with high reduction potential. This yields a data-driven sampling prior that significantly improves the efficiency of stochastic optimization. Our approach synergistically integrates deep learning with conventional randomized search while preserving functional equivalence and minimizing gate count. Experimental evaluation demonstrates that, compared to all optimization levels in Qiskit and BQSKit, our method achieves superior compression (average 12.7% improvement) and faster optimization (3.1× speedup), while incurring lower computational resource overhead.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Machine Learning: Quantum Machine Learning
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

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

Abstract

Translating a general quantum circuit on a specific hardware topology with a reduced set of available gates, also known as transpilation, comes with a substantial increase in the length of the equivalent circuit. Due to decoherence, the quality of the computational outcome can degrade seriously with increasing circuit length. Thus, there is major interest to reduce a quantum circuit to an equivalent circuit which is in its gate count as short as possible. One method to address efficient transpilation is based on approaches known from stochastic optimization, e.g. by using random sampling and token replacement strategies. Here, a core challenge is that these methods can suffer from sampling efficiency, causing long and energy consuming optimization time. As a remedy, we propose in this work 2D neural guided sampling. Thus, given a 2D representation of a quantum circuit, a neural network predicts groups of gates in the quantum circuit, which are likely reducible. Thus, it leads to a sampling prior which can heavily reduce the compute time for quantum circuit reduction. In several experiments, we demonstrate that our method is superior to results obtained from different qiskit or BQSKit optimization levels.

Problem

• Optimizing quantum circuit length for reduced decoherence effects
• Improving sampling efficiency in stochastic quantum transpilation methods
• Using neural networks to predict reducible gate groups in circuits

Innovation

• Neural network predicts reducible quantum gate groups
• 2D representation guides efficient circuit sampling
• Reduces compute time for quantum circuit optimization