Caltech Logo

IQIM Postdoctoral and Graduate Student Seminar

Friday, November 8, 2019
12:00pm to 1:00pm
Add to Cal
East Bridge 114
Quantum-inspired classical sampling algorithms for machine learning
AndrĂ¡s Gilyen, IQIM Postdoctoral Scholar,

Abstract: We construct an efficient classical analogue of the quantum matrix inversion algorithm (HHL) for low-rank matrices. Inspired by recent work of Tang, assuming sampling access to input data, we implement the pseudoinverse of a low-rank matrix and sample from the solution to the problem Ax=b using fast sampling techniques. We implement the pseudo-inverse by finding an approximate singular value decomposition of A via subsampling, then inverting the singular values. In principle, the approach can also be used to apply any desired "smooth" function to the singular values. Since many quantum algorithms can be expressed as a singular value transformation problem, our results also imply that most low-rank quantum machine-learning algorithms can be effectively "dequantised" into classical sampling algorithms.

For more information, please contact Marcia Brown by phone at 626-395-4013 or by email at marciab@caltech.edu.