Optimal false discovery control of minimax estimators
From MaRDI portal
Publication:6103221
Abstract: Two major research tasks lie at the heart of high dimensional data analysis: accurate parameter estimation and correct support recovery. The existing literature mostly aims for either the best parameter estimation or the best model selection result, however little has been done to understand the potential interaction between the estimation precision and the selection behavior. In this work, our minimax result shows that an estimator's performance of type I error control directly links with its estimation error rate, and reveals a trade-off phenomenon between the rate of convergence and the false discovery control: to achieve better accuracy, one risks yielding more false discoveries. In particular, we characterize the false discovery control behavior of rate optimal and rate suboptimal estimators under different sparsity regimes, and discover a rigid dichotomy between these two estimators under near-linear and linear sparsity settings. In addition, this work provides a rigorous explanation to the incompatibility phenomenon between selection consistency and rate minimaxity which has been frequently observed in the high dimensional literature.
Cites work
- A general framework for Bayes structured linear models
- Adapting to unknown sparsity by controlling the false discovery rate
- Asymptotic Bayes-optimality under sparsity of some multiple testing procedures
- Bayesian estimation of sparse signals with a continuous spike-and-slab prior
- Bayesian shrinkage towards sharp minimaxity
- Calibration and empirical Bayes variable selection
- Dirichlet-Laplace priors for optimal shrinkage
- Distribution-free multiple testing
- False discoveries occur early on the Lasso path
- Gaussian model selection
- High-dimensional variable selection with reciprocal \(L_{1}\)-regularization
- scientific article; zbMATH DE number 720689 (Why is no real title available?)
- scientific article; zbMATH DE number 845714 (Why is no real title available?)
- Local asymptotic coding and the minimum description length
- Minimax Rates of Estimation for High-Dimensional Linear Regression Over \ell_q-Balls
- Minimax risk over \(l_ p\)-balls for \(l_ q\)-error
- Model selection and sharp asymptotic minimaxity
- Nearly optimal Bayesian shrinkage for high-dimensional regression
- Nearly unbiased variable selection under minimax concave penalty
- Needles and straw in a haystack: posterior concentration for possibly sparse sequences
- Needles and straw in haystacks: Empirical Bayes estimates of possibly sparse sequences
- On spike and slab empirical Bayes multiple testing
- On the asymptotic properties of SLOPE
- Rate minimaxity of the Lasso and Dantzig selector for the \(l_{q}\) loss in \(l_{r}\) balls
- Sharp Thresholds for High-Dimensional and Noisy Sparsity Recovery Using $\ell _{1}$-Constrained Quadratic Programming (Lasso)
- SLOPE is adaptive to unknown sparsity and asymptotically minimax
- SLOPE-adaptive variable selection via convex optimization
- The Covariance Inflation Criterion for Adaptive Model Selection
- The horseshoe estimator: posterior concentration around nearly black vectors
- Variable Selection via Nonconcave Penalized Likelihood and its Oracle Properties
- Variable selection with Hamming loss
Cited in
(3)
This page was built for publication: Optimal false discovery control of minimax estimators
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6103221)
