EconBase
← All papers

Minimax Semiparametric Learning With Approximate Sparsity

Jelena Bradic, Victor Chernozhukov, Whitney K. Newey, Yinchu Zhu

arXiv 27 Dec 2019 · Mathematics — Statistics Theory · 4 citations (OpenAlex)

arXiv:1912.12213 · PDF · DOI · OpenAlex · Extracted main text

Abstract

Estimating linear, mean-square continuous functionals is a pivotal challenge in statistics. In high-dimensional contexts, this estimation is often performed under the assumption of exact model sparsity, meaning that only a small number of parameters are precisely non-zero. This excludes models where linear formulations only approximate the underlying data distribution, such as nonparametric regression methods that use basis expansion such as splines, kernel methods or polynomial regressions. Many recent methods for root-$n$ estimation have been proposed, but the implications of exact model sparsity remain largely unexplored. In particular, minimax optimality for models that are not exactly sparse has not yet been developed. This paper formalizes the concept of approximate sparsity through classical semi-parametric theory. We derive minimax rates under this formulation for a regression slope and an average derivative, finding these bounds to be substantially larger than those in low-dimensional, semi-parametric settings. We identify several new phenomena. We discover new regimes where rate double robustness does not hold, yet root-$n$ estimation is still possible. In these settings, we propose an estimator that achieves minimax optimal rates. Our findings further reveal distinct optimality boundaries for ordered versus unordered nonparametric regression estimation.

Citation extraction

74
references
200
in-text mentions
85
distinct cited
11
self-citations
63,270
main-text words

appendix boundary found by none_found · 100% 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
1Javanmard, A. and Montanari, A (2018) Debiasing the lasso: Optimal sample size for gaussian designs1.000137100%
2Cai, T. T. and Guo, Z (2017) Confidence intervals for high-dimensional linear regression: Minimax rates and adaptivity1.000118100%
3Chernozhukov, V., Chetverikov, D., Demirer, M., Duflo, E., Hansen, C… (2018) Double/debiased machine learning for treatment and structural parameters self1.00094100%
4Belloni, A., Chernozhukov, V., and Hansen, C (2014) Inference on treatment effects after selection among high-dimensional controls self1.00083100%
5Javanmard, A. and Montanari, A (2014) Confidence intervals and hypothesis testing for high-dimensional regression1.00075100%
6Van de Geer, S., Bühlmann, P., Ritov, Y., and Dezeure, R (2014) On asymptotically optimal confidence regions and tests for high-dimensional models1.00075100%
7Hirshberg, D. A. and Wager, S (2021) Augmented minimax linear estimation1.00074100%
8Tsybakov, A. B (2009) Introduction to Nonparametric Estimation1.00073100%
9Chernozhukov, V., Newey, W. K., and Singh, R (2018) Learning l2 continuous regression functionals via regularized riesz representers self1.00055100%
10Athey, S., Imbens, G. W., and Wager, S (2018) Approximate residual balancing: De-biased inference of average treatment effects in high dimensions1.00054100%

Showing the top 10 of 85 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
1Automatic Debiased Machine Learning of Structural Parameters with General Conditional Moments0.92843
2Assumption-lean Falsification Tests of Rate Double-Robustness of Double-Machine-Learning Estimators0.73732
3Method-of-Moments Inference for GLMs and Doubly Robust Functionals under Proportional Asymptotics0.51121
4Penalized GMM Framework for Inference on Functionals of Nonparametric Instrumental Variable Estimators0.51122
5Structure-agnostic Optimality of Doubly Robust Learning for Treatment Effect Estimation0.40511
6An Introduction to Double/Debiased Machine Learning0.40511
7Sharp Structure-Agnostic Lower Bounds for General Linear Functional Estimation0.40511
8Welfare Analysis in Dynamic Models0.00011