Quantum Algorithm to Cubic Spline Interpolation

Abstract: HHL algorithm \cite{harrow} to solve linear system is a powerful and efficient quantum technique to deal with many matrix operations (such as matrix multiplication, powers and inversion). It inspires many applications in quantum machine learning \cite{biamonte, dunjko}. However, due to the restrictions of HHL algorithm itself, many quantum machine learning algorithms also share one or two restrictions. The most common restrictions include quantum state preparation, condition number and Hamiltonian simulation. In this work, we first give an efficient quantum algorithm to achieve quantum state preparation, which actually achieves an exponential speedup than the algorithms given in \cite{clader,lloyd13}. Then we provide an application of HHL algorithm in cubic spline interpolation problem. We will show that in this problem, the condition number is small, the preparation of quantum state is efficient based on the new algorithm we proposed and the Hamiltonian simulation is efficiently implemented. So the quantum algorithm obtained by HHL algorithm towards this problem actually achieves an exponential speedup than any classical algorithm with no restrictions. This can be viewed as another application of HHL algorithm with no restrictions after the work of Clader et al \cite{clader} in studying electromagnetic scattering cross-section.