ℓ1-penalized quantile regression in high-dimensional sparse models

Abstract

We consider median regression and, more generally, a possibly infinite collection of quantile regressions in high-dimensional sparse models. In these models the number of regressors p is very large, possibly larger than the sample size n, but only at most s regressors have a non-zero impact on each conditional quantile of the response variable, where s grows more slowly than n. Since ordinary quan-tile regression is not consistent in this case, we consider ℓ1-penalized quantile regression (ℓ1-QR), which penalizes the ℓ1-norm of regression coefficients, as well as the post-penalized QR estimator (post-ℓ1-QR), which applies ordinary QR to the model selected by ℓ1-QR. First, we show that under general conditions ℓ1-QR is consistent at the near-oracle rate s/n log(p ∨ n), uniformly in the compact set U ⊂ (0, 1) of quantile indices. In deriving this result, we propose a partly pivotal, data-driven choice of the penalty level and show that it satisfies the requirements for achieving this rate. Second, we show that under similar conditions post-ℓ1-QR is consistent at the near-oracle rate s/n log(p ∨ n), uniformly over U, even if the ℓ1-QR-selected models miss some components of the true models, and the rate could be even closer to the oracle rate otherwise. Third, we characterize conditions under which ℓ1-QR contains the true model as a submodel, and derive bounds on the dimension of the selected model, uniformly over U; we also provide conditions under which hard-thresholding selects the minimal true model, uniformly over U.

Adaptive Lasso-Type Estimation for Multivariate Diffusion Processes

“…In this particular experiment, we also test the post-LASSO estimation as in Belloni and Chernozhukov (2011). This means that we run the QMLE procedure on the model selected by the LASSO method, which is the true model.…”

TheL1penalized LAD estimator for high dimensional linear regression

“…It is worth noting that in the proof of lemma 1 of [23], the authors did not prove the convergence in the last step is uniform, hence the proof is incomplete. In a recent paper [2], the quantile regression model was considered and L 1 penalized method was proposed. Properties of the estimator were presented under restricted eigenvalue type conditions and smooth assumptions on the density function of the noise.…”

Tail Event Driven ASset allocation: evidence from equity and mutual funds’ markets

“…L 1 -penalty is considered to nullify "excessive" coefficients (Belloni and Chernozhukov [2011]). Simple lasso-penalized QR optimisation problem is:…”