Balancing Statistical and Computational Precision: A General Theory and Applications to Sparse Regression
arXiv:1609.07195 · doi:10.1109/TIT.2022.3203857
Abstract
Modern technologies are generating ever-increasing amounts of data. Making use of these data requires methods that are both statistically sound and computationally efficient. Typically, the statistical and computational aspects are treated separately. In this paper, we propose an approach to entangle these two aspects in the context of regularized estimation. Applying our approach to sparse and group-sparse regression, we show that it can improve on standard pipelines both statistically and computationally.
References in corpus (9)
- Nearly unbiased variable selection under minimax concave penalty
- High-dimensional graphs and variable selection with the Lasso
- On the conditions used to prove oracle results for the Lasso
- On the Prediction Performance of the Lasso
- Safe Feature Elimination for the LASSO and Sparse Supervised Learning Problems
- A Practical Scheme and Fast Algorithm to Tune the Lasso With Optimality Guarantees
- GAP Safe Screening Rules for Sparse-Group-Lasso
- Path Following and Empirical Bayes Model Selection for Sparse Regression
- The Group Square-Root Lasso: Theoretical Properties and Fast Algorithms