ERROR MITIGATION ON NOISY QUANTUM SYSTEMS USING MACHINE LEARNING MODELS: A CASE STUDY ON VARIATIONAL QUANTUM EIGENSOLVER (VQE) ENERGY ESTIMATION Maudina Rohmah, Teguh Budi Prayitno, Yanoar Pribadi Sarwono
Physics Department, Faculty of Mathematics and Natural Sciences, Jakarta State University
Quantum Physics Research Center, National Research and Innovation Agency
Abstract
Quantum computers present a promising solution for solving computational problems that are intractable for classical computers, such as simulating quantum systems in chemistry and materials science. One widely used algorithm is the Variational Quantum Eigensolver (VQE), which estimates the ground-state energy of molecules. However, current quantum hardware is still limited by significant noise, which degrades the accuracy of computational results. To address this issue, this study proposes a machine learning-based error mitigation approach. The implemented models include Random Forest (RF), Multi-Layer Perceptron (MLP), Quantum Neural Network (QNN), and Support Vector Regression (SVR). Simulation results show that the RF and SVR models consistently reconstruct energy values close to the ideal, with lower absolute errors and stable predictions across varying bond lengths. Meanwhile, the QNN model exhibits significant deviation from the ideal energy pattern, although it shows potential for further development in hybrid systems. This approach demonstrates that classical machine learning techniques can effectively enhance the reliability of quantum computations under noisy conditions.
