GSC-QEMit: A Telemetry-Driven Hierarchical Forecast-and-Bandit Framework for Adaptive Quantum Error Mitigation

2026-04-27

AI Summary

This work addresses the challenge of balancing error mitigation strength and execution overhead in near-term quantum devices subject to time-varying noise. We propose an adaptive error mitigation framework that, for the first time, integrates context clustering via an incremental hierarchical self-organizing map, uncertainty-aware fidelity degradation prediction using subsampled Gaussian processes, and a cost-aware contextual multi-armed bandit based on Thompson sampling. This integration enables circuit-agnostic, workload-adaptive strategy switching without requiring circuit-specific customization. Experimental results across multiple benchmark circuits demonstrate that our approach improves average logical fidelity by 9.0%, substantially reduces redundant aggressive interventions, and achieves an excellent trade-off between fidelity enhancement and computational cost.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Search and Optimization: Learning to Search
• Reasoning under Uncertainty: Stochastic Optimization

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: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Quantum error mitigation (QEM) is essential for extracting reliable results from near-term quantum devices, yet practical deployments must balance mitigation strength against runtime overhead under time-varying noise. We introduce \emph{GSC-QEMit}, a telemetry-driven, \textbf{context--forecast--bandit} framework for \emph{adaptive} mitigation that switches between lightweight suppression and heavier intervention as drift evolves. GSC-QEMit composes three coupled modules: (G) a Growing Hierarchical Self-Organizing Map (GHSOM) that clusters streaming telemetry into operating contexts; (S) an uncertainty-aware subsampled Gaussian-process forecaster that predicts short-horizon fidelity degradation; and (C) a cost-aware contextual multi-armed bandit (CMAB) that selects mitigation actions via Thompson sampling with explicit intervention cost. We evaluate GSC-QEMit on benchmark circuit families (GHZ, Quantum Fourier Transform, and Grover search) under nonstationary noise regimes simulated in Qiskit Aer, using an instrumented testbed where action labels correspond to graded mitigation intensity. Across Clifford, non-Clifford, and structured workloads, GSC-QEMit improves average logical fidelity by \textbf{+9.0\%} relative to unmitigated execution while reducing unnecessary heavy interventions by reserving them for inferred noise spikes. The resulting policies exhibit a favorable fidelity--cost trade-off and transfer across the evaluated workloads without circuit-specific tuning.

Problem

• Quantum Error Mitigation
• Time-varying Noise
• Runtime Overhead
• Adaptive Mitigation
• Fidelity-Cost Trade-off

Innovation

• adaptive quantum error mitigation
• contextual multi-armed bandit
• telemetry-driven forecasting
• hierarchical self-organizing map
• nonstationary noise