Recursive Quantile Estimation: Non-Asymptotic Confidence Bounds

This paper considers the recursive estimation of quantiles using the stochastic gradient descent (SGD) algorithm with Polyak-Ruppert averaging. The algorithm offers a computationally and memory efficient alternative to the usual empirical estimator. Our focus is on studying the non-asymptotic behavior by providing exponentially decreasing tail probability bounds under mild assumptions on the smoothness of the density functions. This novel non-asymptotic result is based on a bound of the moment generating function of the SGD estimate. We apply our result to …

algorithm apply arm assumptions behavior confidence focus function gradient identification memory novel paper probability quantile recursive stochastic studying