Implementing regularization implicitly via approximate eigenvector computation

  • Mahoney M
  • Orecchia L
  • 68

    Readers

    Mendeley users who have this article in their library.
  • 0

    Citations

    Citations of this article.

Abstract

Regularization is a powerful technique for extracting useful information from noisy data. Typically, it is implemented by adding some sort of norm constraint to an objective function and then exactly optimizing the modified objective function. This procedure often leads to optimization problems that are computationally more expensive than the original problem, a fact that is clearly problematic if one is interested in large-scale applications. On the other hand, a large body of empirical work has demonstrated that heuristics, and in some cases approximation algorithms, developed to speed up computations sometimes have the side-effect of performing regularization implicitly. Thus, we consider the question: What is the regularized optimization objective that an approximation algorithm is exactly optimizing? We address this question in the context of computing approximations to the smallest nontrivial eigenvector of a graph Laplacian; and we consider three random-walk-based procedures: one based on the heat kernel of the graph, one based on computing the the PageRank vector associated with the graph, and one based on a truncated lazy random walk. In each case, we provide a precise characterization of the manner in which the approximation method can be viewed as implicitly computing the exact solution to a regularized problem. Interestingly, the regularization is not on the usual vector form of the optimization problem, but instead it is on a related semidefinite program.

Author-supplied keywords

  • approximate eigenvector computation
  • lementing regularization implicitly via

Get free article suggestions today

Mendeley saves you time finding and organizing research

Sign up here
Already have an account ?Sign in

Find this document

Authors

  • Michael W Mahoney

  • Lorenzo Orecchia

Cite this document

Choose a citation style from the tabs below

Save time finding and organizing research with Mendeley

Sign up for free