EconBase
← All papers

Sparse Quantile Regression

Le-Yu Chen, Sokbae Lee

arXiv 19 Jun 2020 · Statistics — Methodology · publishedJournal of Econometrics (2023) · 7 citations (OpenAlex)

arXiv:2006.11201 · PDF · DOI · OpenAlex · Extracted main text

Abstract

We consider both $\ell _{0}$-penalized and $\ell _{0}$-constrained quantile regression estimators. For the $\ell _{0}$-penalized estimator, we derive an exponential inequality on the tail probability of excess quantile prediction risk and apply it to obtain non-asymptotic upper bounds on the mean-square parameter and regression function estimation errors. We also derive analogous results for the $\ell _{0}$-constrained estimator. The resulting rates of convergence are nearly minimax-optimal and the same as those for $\ell _{1}$-penalized and non-convex penalized estimators. Further, we characterize expected Hamming loss for the $\ell _{0}$-penalized estimator. We implement the proposed procedure via mixed integer linear programming and also a more scalable first-order approximation algorithm. We illustrate the finite-sample performance of our approach in Monte Carlo experiments and its usefulness in a real data application concerning conformal prediction of infant birth weights (with $n\approx 10^{3}$ and up to $p>10^{3}$). In sum, our $\ell _{0}$-based method produces a much sparser estimator than the $\ell _{1}$-penalized and non-convex penalized approaches without compromising precision.

Citation extraction

44
references
95
in-text mentions
44
distinct cited
3
self-citations
12,865
main-text words

appendix boundary found by appendix_command · 63% of the source is main text. Read the extracted text to check this.

Most heavily cited references

The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.

ReferenceIntensityMentionsSectionsMain text
1Belloni and Chernozhukov (2011) $_1$-penalized quantile regression in high-dimensional sparse models1.000103100%
2Bertsimas, King, and Mazumder (2016) Best subset selection via a modern optimization lens0.96510490%
3Wang (2019) $L_1$-regularized Quantile Regression with Many Regressors under Lean Assumptions0.87482100%
4Wang, Wu, and Li (2012) Quantile Regression for Analyzing Heterogeneity in Ultra-High Dimension0.81142100%
5Romano, Patterson, and Candes (2019) Conformalized quantile regression0.81142100%
6Massart and Nédélec (2006) Risk bounds for statistical learning0.7374350%
7Fan, Fan, and Barut (2014) Adaptive Robust Variable Selection0.73732100%
8Huang, Jiao, Liu, and Lu (2018) A Constructive Approach to $L_0$ Penalized Regression0.73732100%
9Wang and He (2022) Analysis of Global and Local Optima Of Regularized Quantile Regression in High Dimensions: A Subgradient Approach0.73732100%
10Nesterov (2005) Smooth minimization of non-smooth functions0.64441100%

Showing the top 10 of 44 scored citations.

Cited by, within the corpus

arXiv econ.EM papers that cite this one, ranked by how heavily they lean on it.

Citing paperIntensityMentionsSections
1Fast Inference for Quantile Regression with Tens of Millions of Observations0.40511