题目：A Constructive Approach to L0-Penalized Regression
报告人：刘妍岩 教授 (武汉大学 数学与统计学院）
【摘要】We develop a constructive approach to estimating sparse, high-dimensional linear regression models. The approach is a computational algorithm motivated from the KKT conditions for the -penalized least squares solutions. It generates a sequence of solutions iteratively, based on support detection using primal and dual information and root finding. We refer to the algorithm as SDAR for brevity. Under a sparse Rieze condition on the design matrix and certain other conditions, we show that with high probability,the estimation error of the solution sequence decays exponentially to the minimax error bound in steps; and under a mutual coherence condition and certain other conditions, the estimation error decays to the optimal error bound in $O(\log(R))$ steps,where is the number of important predictors, is the relative magnitude of the nonzero target coefficients. Computational complexity analysis shows that the cost of SDAR is per iteration. Moreover the oracle least squares estimator can be exactly recovered with high probability at the same cost if we know the sparsity level. We also consider an adaptive version of SDAR to make it more practical in applications. Numerical comparisons with Lasso, MCP and greedy methods demonstrate that SDAR is competitive with or outperforms them in accuracy and efficiency.
Copyright © 2018 同济大学数学科学学院 版权所有.