Computational Performance Bounds Prediction in Quantum Computing with Unstable Noise

2025-07-22

AI Summary

Accurately predicting performance bounds of quantum computations under time-varying noise remains challenging due to the dynamic and heterogeneous nature of noise sources. Method: This paper introduces QuBound—a novel framework that jointly predicts rigorous upper and lower performance bounds (rather than point estimates) by integrating performance decomposition with an LSTM-based encoder. It disentangles noise sources from historical performance trajectories and jointly encodes circuit topology and time-resolved noise characteristics to construct a temporal-aware boundary prediction model. Contribution/Results: QuBound achieves over a 10× reduction in prediction interval width compared to existing analytical methods. Relative to quantum circuit simulation and learning-based baselines, it accelerates inference by more than six orders of magnitude (10⁶×), while guaranteeing that all predicted bounds strictly contain the true performance values. This strict containment significantly enhances reliability for quantum task scheduling and system-level resource management.

Technology Category

• Machine Learning: Quantum Machine Learning
• Planning, Routing, and Scheduling: Learning for Planning and Scheduling
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization

Abstract

Quantum computing has significantly advanced in recent years, boasting devices with hundreds of quantum bits (qubits), hinting at its potential quantum advantage over classical computing. Yet, noise in quantum devices poses significant barriers to realizing this supremacy. Understanding noise's impact is crucial for reproducibility and application reuse; moreover, the next-generation quantum-centric supercomputing essentially requires efficient and accurate noise characterization to support system management (e.g., job scheduling), where ensuring correct functional performance (i.e., fidelity) of jobs on available quantum devices can even be higher-priority than traditional objectives. However, noise fluctuates over time, even on the same quantum device, which makes predicting the computational bounds for on-the-fly noise is vital. Noisy quantum simulation can offer insights but faces efficiency and scalability issues. In this work, we propose a data-driven workflow, namely QuBound, to predict computational performance bounds. It decomposes historical performance traces to isolate noise sources and devises a novel encoder to embed circuit and noise information processed by a Long Short-Term Memory (LSTM) network. For evaluation, we compare QuBound with a state-of-the-art learning-based predictor, which only generates a single performance value instead of a bound. Experimental results show that the result of the existing approach falls outside of performance bounds, while all predictions from our QuBound with the assistance of performance decomposition better fit the bounds. Moreover, QuBound can efficiently produce practical bounds for various circuits with over 106 speedup over simulation; in addition, the range from QuBound is over 10x narrower than the state-of-the-art analytical approach.

Problem

• Predict computational bounds in quantum computing with unstable noise
• Characterize noise impact for quantum system management and job scheduling
• Overcome efficiency and scalability issues in noisy quantum simulation

Innovation

• Data-driven workflow for quantum performance prediction
• Decomposes historical traces to isolate noise sources
• LSTM network processes circuit and noise information