# De-biasing the Lasso: Optimal Sample Size for Gaussian Designs

arXiv: https://arxiv.org/abs/1508.02757 · HTML: https://mlsanity.com/paper/1508.02757/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Aug 2015.

## Built on by (most cited first, 30 of 35)

- [High-dimensional robust regression under heavy-tailed data: Asymptotics and Universality](https://mlsanity.com/paper/2309.16476/) (2023)
- [DoubleML -- An Object-Oriented Implementation of Double Machine Learning in R](https://mlsanity.com/paper/2103.09603/) (2021)
- [Debiased Machine Learning without Sample-Splitting for Stable Estimators](https://mlsanity.com/paper/2206.01825/) (2022)
- [DRCFS: Doubly Robust Causal Feature Selection](https://mlsanity.com/paper/2306.07024/) (2023)
- [A flexible empirical Bayes approach to multiple linear regression and connections with penalized regression](https://mlsanity.com/paper/2208.10910/) (2022)
- [Prediction Sets for High-Dimensional Mixture of Experts Models](https://mlsanity.com/paper/2210.16710/) (2022)
- [The Flip Side of the Reweighted Coin: Duality of Adaptive Dropout and Regularization](https://mlsanity.com/paper/2106.07769/) (2021)
- [Asymptotic normality of robust M-estimators with convex penalty](https://mlsanity.com/paper/2107.03826/) (2021)
- [Spectral Estimators for Structured Generalized Linear Models via Approximate Message Passing](https://mlsanity.com/paper/2308.14507/) (2023)
- [Matrix Denoising with Doubly Heteroscedastic Noise: Fundamental Limits and Optimal Spectral Methods](https://mlsanity.com/paper/2405.13912/) (2024)
- [Inference on Optimal Dynamic Policies via Softmax Approximation](https://mlsanity.com/paper/2303.04416/) (2023)
- [On the Variance, Admissibility, and Stability of Empirical Risk Minimization](https://mlsanity.com/paper/2305.18508/) (2023)
- [Optimally taming biases in black-box models for efficient semiparametric estimation](https://mlsanity.com/paper/2606.06368/) (2026)
- [Chi-square and normal inference in high-dimensional multi-task regression](https://mlsanity.com/paper/2107.07828/) (2021)
- [Distributed Sparse Feature Selection in Communication-Restricted Networks](https://mlsanity.com/paper/2111.02802/) (2021)
- [On the instrumental variable estimation with many weak and invalid instruments](https://mlsanity.com/paper/2207.03035/) (2022)
- [Uncertainty quantification for learned ISTA](https://mlsanity.com/paper/2309.07982/) (2023)
- [Non-Asymptotic Uncertainty Quantification in High-Dimensional Learning](https://mlsanity.com/paper/2407.13666/) (2024)
- [Optimal and Provable Calibration in High-Dimensional Binary Classification: Angular Calibration and Platt Scaling](https://mlsanity.com/paper/2502.15131/) (2025)
- [Spatially relaxed inference on high-dimensional linear models](https://mlsanity.com/paper/2106.02590/) (2021)
- [Controlling the False Split Rate in Tree-Based Aggregation](https://mlsanity.com/paper/2108.05350/) (2021)
- [Majority Vote for Distributed Differentially Private Sign Selection](https://mlsanity.com/paper/2209.04419/) (2022)
- [Mixed Semi-Supervised Generalized-Linear-Regression with Applications to Deep-Learning and Interpolators](https://mlsanity.com/paper/2302.09526/) (2023)
- [Stability of a Generalized Debiased Lasso with Applications to Resampling-Based Variable Selection](https://mlsanity.com/paper/2405.03063/) (2024)
- [Leave-One-Out Analysis for Nonconvex Robust Matrix Completion with General Thresholding Functions](https://mlsanity.com/paper/2407.19446/) (2024)
- [Optimal use of a black-box learner in semiparametric estimation](https://mlsanity.com/paper/2607.21541/) (2026)
- [Statistical Inference for High-Dimensional Linear Regression with Blockwise Missing Data](https://mlsanity.com/paper/2106.03344/) (2021)
- [Distributed Sparse Linear Regression under Communication Constraints](https://mlsanity.com/paper/2301.04022/) (2023)
- [Information criteria for structured parameter selection in high dimensional tree and graph models](https://mlsanity.com/paper/2306.14026/) (2023)
- [Triple/Debiased Lasso for Statistical Inference of Conditional Average Treatment Effects](https://mlsanity.com/paper/2403.03240/) (2024)

## Abstract (arXiv)

Performing statistical inference in high-dimension is an outstanding challenge. A major source of difficulty is the absence of precise information on the distribution of high-dimensional estimators. Here, we consider linear regression in the high-dimensional regime pgg n. In this context, we would like to perform inference on a high-dimensional parameters vector θ^*∈mathbb Rp. Important progress has been achieved in computing confidence intervals for single coordinates θ^*i. A key role in these new methods is played by a certain debiased estimator hatθrm d that is constructed from the Lasso. Earlier work establishes that, under suitable assumptions on the design matrix, the coordinates of hatθrm d are asymptotically Gaussian provided θ^* is s0-sparse with s0 = o(√n/log p ). The condition s0 = o(√n/ log p ) is stronger than the one for consistent estimation, namely s0 = o(n/ log p). We study Gaussian designs with known or unknown population covariance. When the covariance is known, we prove that the debiased estimator is asymptotically Gaussian under the nearly optimal condition s0 = o(n/ (log p)2). Note that earlier work was limited to s0 = o(√n/log p) even for perfectly known covariance. The same conclusion holds if the population covariance is unknown but can be estimated sufficiently well, e.g. under the same sparsity conditions on the inverse covariance as assumed by earlier work. For intermediate regimes, we describe the trade-off between sparsity in the coefficients and in the inverse covariance of the design. We further discuss several applications of our results to high-dimensional inference. In particular, we propose a new estimator that is minimax optimal up to a factor 1+on(1) for i.i.d. Gaussian designs.