Competing with the Empirical Risk Minimizer in a Single Pass
Proceedings of The 28th Conference on Learning Theory, PMLR 40:728-763, 2015.
In many estimation problems, e.g. linear and logistic regression, we wish to minimize an unknown objective given only unbiased samples of the objective function. Furthermore, we aim to achieve this using as few samples as possible. In the absence of computational constraints, the minimizer of a sample average of observed data – commonly referred to as either the empirical risk minimizer (ERM) or the M-estimator – is widely regarded as the estimation strategy of choice due to its desirable statistical convergence properties. Our goal in this work is to perform as well as the ERM, on \emphevery problem, while minimizing the use of computational resources such as running time and space usage. We provide a simple streaming algorithm which, under standard regularity assumptions on the underlying problem, enjoys the following properties: \beginenumerate \item The algorithm can be implemented in linear time with a single pass of the observed data, using space linear in the size of a single sample. \item The algorithm achieves the same statistical rate of convergence as the empirical risk minimizer on every problem, even considering constant factors. \item The algorithm’s performance depends on the initial error at a rate that decreases super-polynomially. \item The algorithm is easily parallelizable. \endenumerate Moreover, we quantify the (finite-sample) rate at which the algorithm becomes competitive with the ERM.