A0228
Title: Learning high dimensional multi-response linear models with quantum optimization
Authors: Yuan Ke - University of Georgia (United States) [presenting]
Abstract: A hybrid quantum computing algorithm is used to study linear regression models for high-dimensional multi-response data. An intuitively appealing estimation method is proposed based on identifying the linearly independent columns in the coefficient matrix. The approach relaxes the low-rank constraint in the existing literature and allows the rank to diverge with dimensions. A novel quantum optimization algorithm selects the linearly independent columns significantly faster than classical methods implemented on electronic computers are proved. The proposed estimation procedure enjoys desirable theoretical properties. Intensive numerical experiments are also conducted to demonstrate the finite sample performance of the proposed method, and a comparison is made with some popular competitors. The results show that this method outperforms all alternative techniques under various circumstances.
