ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 1206.4638
30
24

Efficient Euclidean Projections onto the Intersection of Norm Balls

18 June 2012
Adams Wei Yu
Hao Su
Li Fei-Fei
ArXivPDFHTML
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 ℓ1\ell_1ℓ1​ and ℓ1,q\ell_{1,q}ℓ1,q​ norm balls (q=2or∞)(q=2\text{or}\infty)(q=2or∞) 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+glog⁡g)O(n+g\log g)O(n+glogg) for q=2q=2q=2 and O(nlog⁡n)O(n\log n)O(nlogn) for q=∞q=\inftyq=∞, where nnn is the dimensionality of the vector to be projected and ggg 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