[1]  Burges C J C. A tutorial on support vector machines for pattern recognition. Data Mining and Knowledge Discovery, 1998, 2: 121--167

[2]  Blum A. Random projection, margins, kernels, and feature-selection. Lecture Notes in Computer Sciences, 2006, 3940: 52--68

[3]  Cand\`{e}s E J. Compressive sampling. Proceedings of the International Congress of Mathematicians, 2006, 3: 1433--1452

[4]  Cand\`{e}s E J. The restricted isometry property and its implications for compressed sensing. Compte Rendus Mathematique, 2008, 346: 589--592

[5]  Cand\`{e}s, E J, Tao T. Near-optimal signal recovery from random projections: universal encoding strategies. IEEE Trans Infor Theory, 2006, 52: 5406--5425

[6]  Calderbank R, Jafarpour Schapire S R. Compressed Learning: Universal Sparse Dimensionality Reduction and Learning in the Measurement Domain. Technical Report. Houston, TX: Rice University, 2009

[7]  Cucker F, Smale S. On the mathematical foundations of learning. Bull Amer Math Soc (New Series), 2001, 39: 1--49

[8]  Donoho D L. Compressed sensing.IEEE Trans Infor Theory, 2006, 52: 1289--1306

[9]  Lee W S, Bartlett P L, Williamson R C. The importance of convexity in learning with least square loss. IEEE Trans Infor Theory, 1998, 44: 1974--1980

[10]  Maillard O A, Munos R. Linear regression with random projections.The Journal of Machine Learning Research, 2012, 13(1): 2735--2772

[11]  Maillard O A, Munos R.Compressed least-squares regression. In Proceedings of Advances in Neural Information
Processing Systems, 2009, 22: 1213--1221

[12]  Rahimi A, Recht B. Random features for large-scale kernel machines. In Proceedings of Advances in Neural Information Processing Systems, 2007, 20: 1160--1168

[13]  Tibshirani R. Regression shrinkage and selection via the Lasso. J Royal Statis Soc (Series B), 1996, 58(1): 267--288

[14]  Tikhonov A N. Solution of incorrectly formulated problems and the regularization method. Soviet Mathematics Doklady, 1963, 4: 1035--1038

[15]  Vapnik V N. An overview of statistical learning theory. IEEE Trans Neural Networks, 1999, 10: 988--999

[16]  Wu Q, Ying Y M, Zhou D X. Learning rates of least-square regularized regression. Found Comput Math, 2006, 6: 171--192

[17]  Zhou D X. The covering number in learning theory. J Complexity, 2002, 18: 739--767

[18]  Zhang T. Covering number bounds of certain regularized linear function classes. J Mach Lear Res, 2002, 2: 527--550

[19]  Zhou S H, Lafferty J,  Wasserman L. Compressed regression. IEEE Trans Infor Theory, 2009, 55: 846--866