37
24

Efficient Euclidean Projections onto the Intersection of Norm Balls

Abstract

Using sparse-inducing norms to learn robust models has received increasing attention from many fields for its attractive properties. Projection-based methods have been widely applied to learning tasks constrained by such norms. As a key building block of these methods, an efficient operator for Euclidean projection onto the intersection of 1\ell_1 and 1,q\ell_{1,q} norm balls (q=2or)(q=2\text{or}\infty) is proposed in this paper. We prove that the projection can be reduced to finding the root of an auxiliary function which is piecewise smooth and monotonic. Hence, a bisection algorithm is sufficient to solve the problem. We show that the time complexity of our solution is O(n+glogg)O(n+g\log g) for q=2q=2 and O(nlogn)O(n\log n) for q=q=\infty, where nn is the dimensionality of the vector to be projected and gg is the number of disjoint groups; we confirm this complexity by experimentation. Empirical study reveals that our method achieves significantly better performance than classical methods in terms of running time and memory usage. We further show that embedded with our efficient projection operator, projection-based algorithms can solve regression problems with composite norm constraints more efficiently than other methods and give superior accuracy.

View on arXiv
Comments on this paper