English

Spectral Sparsification and Regret Minimization Beyond Matrix Multiplicative Updates

Machine Learning 2015-06-17 v1 Data Structures and Algorithms Optimization and Control Machine Learning

Abstract

In this paper, we provide a novel construction of the linear-sized spectral sparsifiers of Batson, Spielman and Srivastava [BSS14]. While previous constructions required Ω(n4)\Omega(n^4) running time [BSS14, Zou12], our sparsification routine can be implemented in almost-quadratic running time O(n2+ε)O(n^{2+\varepsilon}). The fundamental conceptual novelty of our work is the leveraging of a strong connection between sparsification and a regret minimization problem over density matrices. This connection was known to provide an interpretation of the randomized sparsifiers of Spielman and Srivastava [SS11] via the application of matrix multiplicative weight updates (MWU) [CHS11, Vis14]. In this paper, we explain how matrix MWU naturally arises as an instance of the Follow-the-Regularized-Leader framework and generalize this approach to yield a larger class of updates. This new class allows us to accelerate the construction of linear-sized spectral sparsifiers, and give novel insights on the motivation behind Batson, Spielman and Srivastava [BSS14].

Cite

@article{arxiv.1506.04838,
  title  = {Spectral Sparsification and Regret Minimization Beyond Matrix Multiplicative Updates},
  author = {Zeyuan Allen-Zhu and Zhenyu Liao and Lorenzo Orecchia},
  journal= {arXiv preprint arXiv:1506.04838},
  year   = {2015}
}
R2 v1 2026-06-22T09:54:15.643Z