Quantum algorithm for linear regression

We present a quantum algorithm for fitting a linear regression model to a given data set using the least-squares approach. Differently from previous algorithms which yield a quantum state encoding the optimal parameters, our algorithm outputs these numbers in the classical form. So by running it once, one completely determines the fitted model and then can use it to make predictions on new data at little cost. Moreover, our algorithm works in the standard oracle model, and can handle data sets with nonsparse design matrices. It runs in time $\text{poly}({log}_2\left(N\right),d,\kappa ,1/\epsilon )$, where $N$ is the size of the data set, $d$ is the number of adjustable parameters, $\kappa$ is the condition number of the design matrix, and $\epsilon$ is the desired precision in the output. We also show that the polynomial dependence on $d$ and $\kappa$ is necessary. Thus, our algorithm cannot be significantly improved. Furthermore, we also give a quantum algorithm that estimates the quality of the least-squares fit (without computing its parameters explicitly). This algorithm runs faster than the one for finding this fit, and can be used to check whether the given data set qualifies for linear regression in the first place.