Machine Learning for Practical Quantum Error Mitigation

Join a Qiskit Quantum Seminar where senior Ph.D. candidate Haoran Liao explores how machine learning can effectively address quantum error mitigation challenges in practical quantum computing. Discover how various machine learning models, including linear regression, random forests, multi-layer perceptrons, and graph neural networks, perform when applied to different quantum circuits and device noise profiles. Learn about breakthrough findings showing machine learning models outperforming traditional digital zero noise extrapolation in both accuracy and efficiency for small-scale quantum circuits. Explore practical applications through experiments conducted on quantum hardware using 100 qubits, demonstrating how machine learning methods can effectively replicate other error mitigation techniques while reducing computational overhead. Gain insights into the promising intersection of classical machine learning and practical quantum computation, backed by research conducted during Liao's internship at IBM Quantum under Zlatko Minev's supervision.