Support recovery and sup-norm convergence rates for sparse pivotal estimation
arXiv:2001.05401
Abstract
In high dimensional sparse regression, pivotal estimators are estimators for which the optimal regularization parameter is independent of the noise level. The canonical pivotal estimator is the square-root Lasso, formulated along with its derivatives as a "non-smooth + non-smooth" optimization problem. Modern techniques to solve these include smoothing the datafitting term, to benefit from fast efficient proximal algorithms. In this work we show minimax sup-norm convergence rates for non smoothed and smoothed, single task and multitask square-root Lasso-type estimators. Thanks to our theoretical analysis, we provide some guidelines on how to set the smoothing hyperparameter, and illustrate on synthetic data the interest of such guidelines.
References in corpus (7)
- Simultaneous analysis of Lasso and Dantzig selector
- Square-Root Lasso: Pivotal Recovery of Sparse Signals via Conic Programming
- Taking Advantage of Sparsity in Multi-Task Learning
- Trace Lasso: a trace norm regularization for correlated designs
- Efficient Smoothed Concomitant Lasso Estimation for High Dimensional Regression
- Handling correlated and repeated measurements with the smoothed multivariate square-root Lasso
- On Fast Convergence of Proximal Algorithms for SQRT-Lasso Optimization: Don't Worry About Its Nonsmooth Loss Function