DeepAI AI Chat
Log In Sign Up

Implementing regularization implicitly via approximate eigenvector computation

by   Michael W. Mahoney, et al.
berkeley college
Stanford University

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.


page 1

page 2

page 3

page 4


Regularized Laplacian Estimation and Fast Eigenvector Approximation

Recently, Mahoney and Orecchia demonstrated that popular diffusion-based...

Efficient Computation of Mean Truncated Hitting Times on Very Large Graphs

Previous work has shown the effectiveness of random walk hitting times a...

Convexification of Learning from Constraints

Regularized empirical risk minimization with constrained labels (in cont...

Graph-Based Ascent Algorithms for Function Maximization

We study the problem of finding the maximum of a function defined on the...

"Drunk Man" Saves Our Lives: Route Planning by a Biased Random Walk Mode

Based on the hurricane striking Puerto Rico in 2017, we developed a tran...

A Distributed Laplacian Solver and its Applications to Electrical Flow and Random Spanning Tree Computation

We present a distributed solver for a large and important class of Lapla...