Quantum Algorithm for Linear Regression for Large Feature-Set

Linear Regression is a widely used optimization problem with many practical applications. Adiabatic Quantum Computers are excellent at solving such optimization problems. Current quantum-based solutions allow for datasets having only a small number of features (maximum 32). We have come up with a novel approach that allows for a greater number of features for Linear Regression. We have found that our approach works for a large number of features, ranging from 64 to 128. We obtained a reasonably similar MSE (Mean Squared Error) to that of sklearn's standard Linear Regression class, with a difference that lies between 0.01 and 0.03.