学术报告
A Constructive Approach to Sparse Linear Regression
报告题目：A Constructive Approach to Sparse Linear Regression
报告人 ：Prof. Huang Jian
（University of Iowa and Shanghai University of Finance and Economics，USA）
摘要：We develop a constructive approach to estimating sparse linear regression models in high-dimensions. The proposed approach is a computational algorithm that generates a sequence of solutions iteratively, based on support detection using primal and dual information and root finding according to a modified KKT condition for the L0-penalized least squares criterion. We refer to the proposed algorithm as SDAR for brevity. Under certain regularity conditions on the design matrix and sparsity assumption on the regression coefficients, we show that with high probability, the estimation errors decay exponentially and to the minimax error bound and to the optimal error bound in finitely many steps. Computational complexity analysis shows that the cost of SDAR is O(np) in each step. Simulation studies are conducted to evaluate the performance of SDAR and its comparison with several existing methods.
时间：12月17日（周四）10：45-11：20
地点：首都师大北一区文科楼205
欢迎全体师生积极参加！
