一类零模正则复合优化问题的多阶段凸松弛法
GEP-MSCRA for a Kind of Zero-Norm Regularized Composite Optimization Problem
摘要: 本文从零模函数的变分刻画入手,将这类带有组合性质的优化问题等价转化为具有拟双线性结构且全局Lipshitz连续的优化模型，以此设计了求解零模正则化复合优化问题的多阶段凸松弛方法，并对该方法进行了收敛性分析。
Abstract: This article starts from the variational characterization of zero-norm, then changes such a combi-nation optimization problem to an equivalent model which has bi-linear structure and global Lip-schitz continuous. This article also designed multi-stage convex relaxation methods to solve the zero-norm regularized composite optimization problem, and analyzed the convergence for it.
文章引用：吕佩雯. 一类零模正则复合优化问题的多阶段凸松弛法[J]. 运筹与模糊学, 2019, 9(1): 65-71. https://doi.org/10.12677/ORF.2019.91008

参考文献

[1] Loh, P.L. and Wainwright, M.J. (2015) Regularized M-Estimators with Nonconvexity: Statistical and Algorithmic Theory for Local Optima. Journal of Machine Learning Research, 16, 559-616.
[2] Casasaya, J. and Llibre, J. (2009) Large-Scale Sparse Logistic Regression. ACM Press, New York, 547-556.
[3] Rockafellar, R.T. (1970) Convex Analysis. Princeton University Press.
[4] Bi, S.J., Liu, X.L. and Pan, S.H. (2014) Exact Penalty Decomposition Method for Zero-Norm Minimization Based on MPEC Formulation. SIAM Journal on Scientific Computing, 36, 1451-1477. [Google Scholar] [CrossRef] 
[5] 贲树军. 低秩优化问题的多阶段凸松弛法研究[D]: [博士学位论文]. 广州: 华南理工大学, 2014.
[6] Candes, E.J., Wakin, M.B. and Boyd, S.P. (2008) Enhancing Sparsity by Reweighted l1 Minimization. Journal of Fourier Analysis and Applications, 14, 877-905. [Google Scholar] [CrossRef] 
[7] Schmidt, M., Fung, G. and Rosales, R. (2007) Fast Optimization Methods for l1 Regularization: A Comparative Study and Two New Approaches. Lnai, 4701, 286-297. [Google Scholar] [CrossRef] 
[8] Park, M.Y. and Hastie, T. (2008) L1 Regularized Path Algorithm for Gen-eralized Linear Models. Journal of the Royal Statistical Society: Series B, 69, 659-677. [Google Scholar] [CrossRef] 
[9] Koh, K., Kim, S. and Boyd, S. (2007) An Interior-Point Method for Large-Scale l1-Regularized Logistic Regression. Journal of Machine Learning Research, 8, 1519-1555.
[10] Lee, S., Lee, H., Abbeel, P. and Ng, A.Y. (2006) Efficient l1 Regularized Logistic Regression. National Conference on Artificial Intelligence, 1, 401-408.
[11] Loh, P.L. and Wainwright, M.J. (2015) Regularized M-Estimators with Nonconvexity: Statistical and Algorithmic Theory for Local Optima. Journal of Machine Learning Research, 16, 559-616.
[12] Casasaya, J. and Llibre, J. (2009) Large-Scale Sparse Logistic Regression. ACM Press, New York, 547-556.
[13] Rockafellar, R.T. (1970) Convex Analysis. Princeton University Press.
[14] Bi, S.J. and Pan, S.H. (2017) GEP-MSCRA for Computing the Group Ze-ro-Norm Regularized Least Squares Estimator. arXiv.org.
[15] 贲树军. 低秩优化问题的多阶段凸松弛法研究[D]: [博士学位论文]. 广州: 华南理工大学, 2014.
[16] Candes, E.J., Wakin, M.B. and Boyd, S.P. (2008) Enhancing Sparsity by Reweighted l1 Minimization. Journal of Fourier Analysis and Applications, 14, 877-905. [Google Scholar] [CrossRef] 
[17] Schmidt, M., Fung, G. and Rosales, R. (2007) Fast Optimization Methods for l1 Regularization: A Comparative Study and Two New Approaches. Lnai, 4701, 286-297. [Google Scholar] [CrossRef] 
[18] Park, M.Y. and Hastie, T. (2008) L1 Regularized Path Algorithm for Generalized Linear Models. Journal of the Royal Statistical Society: Series B, 69, 659-677. [Google Scholar] [CrossRef] 
[19] Koh, K., Kim, S. and Boyd, S. (2007) An Interior-Point Method for Large-Scale l1-Regularized Logistic Regression. Journal of Machine Learning Research, 8, 1519-1555.
[20] Lee, S., Lee, H., Abbeel, P. and Ng, A.Y. (2006) Efficient l1 Regularized Logistic Regression. National Conference on Artificial Intelligence, 1, 401-408.

为你推荐