Efficient Euclidean projections in linear time

We consider the problem of computing the Euclidean projection of a vector of length n onto a closed convex set including the l1 ball and the specialized polyhedra employed in (Shalev-Shwartz & Singer, 2006). These problems have played building block roles in solving several l1-norm based sparse learning problems. Existing methods have a worst-case time complexity of O(n log n). In this paper, we propose to cast both Euclidean projections as root finding problems associated with specific auxiliary functions, which can be solved in linear time via bisection. We further make use of the special structure of the auxiliary functions, and propose an improved bisection algorithm. Empirical studies demonstrate that the proposed algorithms are much more efficient than the competing ones for computing the projections.

[1]  A. Ng Feature selection, L1 vs. L2 regularization, and rotational invariance , 2004, Twenty-first international conference on Machine learning - ICML '04.

[2]  Yoram Singer,et al.  Efficient projections onto the l1-ball for learning in high dimensions , 2008, ICML '08.

[3]  Stephen P. Boyd,et al.  An Interior-Point Method for Large-Scale l1-Regularized Logistic Regression , 2007, J. Mach. Learn. Res..

[4]  Stephen P. Boyd,et al.  Convex Optimization , 2004, IEEE Transactions on Automatic Control.

[5]  Yurii Nesterov,et al.  Introductory Lectures on Convex Optimization - A Basic Course , 2014, Applied Optimization.

[6]  E.J. Candes,et al.  An Introduction To Compressive Sampling , 2008, IEEE Signal Processing Magazine.

[7]  David L Donoho,et al.  Compressed sensing , 2006, IEEE Transactions on Information Theory.

[8]  Arkadi Nemirovski,et al.  EFFICIENT METHODS IN CONVEX PROGRAMMING , 2007 .

[9]  Richard P. Brent,et al.  An Algorithm with Guaranteed Convergence for Finding a Zero of a Function , 1971, Comput. J..

[10]  Nathan Srebro,et al.  Iterative Loss Minimization with ` 1-Norm Constraint and Guarantees on Sparsity , 2008 .

[11]  Clifford Stein,et al.  Introduction to Algorithms, 2nd edition. , 2001 .

[12]  R. K. Shyamasundar,et al.  Introduction to algorithms , 1996 .

[13]  R. Tibshirani Regression Shrinkage and Selection via the Lasso , 1996 .

[14]  Yoram Singer,et al.  Efficient Learning of Label Ranking by Soft Projections onto Polyhedra , 2006, J. Mach. Learn. Res..

[15]  Shai Shalev-Shwartz,et al.  Online Learning: Theory, Algorithms, and Applications , 2007 .