Exponentiated) Stochastic Gradient Descent for L1 Constrained Problems
暂无分享,去创建一个
[1] Michael Elad,et al. Optimally sparse representation in general (nonorthogonal) dictionaries via ℓ1 minimization , 2003, Proceedings of the National Academy of Sciences of the United States of America.
[2] Martin Zinkevich,et al. Online Convex Programming and Generalized Infinitesimal Gradient Ascent , 2003, ICML.
[3] Dean P. Foster,et al. The risk inflation criterion for multiple regression , 1994 .
[4] Stéphane Mallat,et al. Matching pursuits with time-frequency dictionaries , 1993, IEEE Trans. Signal Process..
[5] Claudio Gentile,et al. On the generalization ability of on-line learning algorithms , 2001, IEEE Transactions on Information Theory.
[6] Michael A. Saunders,et al. Atomic Decomposition by Basis Pursuit , 1998, SIAM J. Sci. Comput..
[7] Manfred K. Warmuth,et al. Exponentiated Gradient Versus Gradient Descent for Linear Predictors , 1997, Inf. Comput..
[8] R. Tibshirani. Regression Shrinkage and Selection via the Lasso , 1996 .
[9] I. Johnstone,et al. Ideal spatial adaptation by wavelet shrinkage , 1994 .
[10] Terence Tao,et al. The Dantzig selector: Statistical estimation when P is much larger than n , 2005, math/0506081.
[11] Adam Tauman Kalai,et al. Online convex optimization in the bandit setting: gradient descent without a gradient , 2004, SODA '05.
[12] W. Welch. Algorithmic complexity: three NP- hard problems in computational statistics , 1982 .
[13] Alan J. Miller. Subset Selection in Regression , 1992 .
[14] A. Ng. Feature selection, L1 vs. L2 regularization, and rotational invariance , 2004, Twenty-first international conference on Machine learning - ICML '04.