« search calendars« DIMACS Workshop on Randomized Numerical Linear Algebra, Statistics, and Optimization

« Pragmatic Ridge Spectral Sparsification for Large-Scale Graph Learning

Pragmatic Ridge Spectral Sparsification for Large-Scale Graph Learning

September 17, 2019, 11:30 AM - 12:10 PM


Center Hall

Rutgers University

Busch Campus Student Center

604 Bartholomew Rd

Piscataway NJ

Click here for map.

Ioannis Koutis, New Jersey Institute of Technology

The representation and benefits of learning methods based on graph Laplacians, such as Laplacian smoothing or harmonic function solution for semi-supervised learning, are empirically and theoretically well supported. There is an increasing number of very large real-world graphs with a number of edges which is sufficiently large for sparsification algorithms to become practically applicable. Motivated by learning algorithms that employ regularization, we discuss the design and properties of a distributed algorithm for ridge spectral sparsification with demonstrable practical gains. The talk represents joint work with Daniele Calandriello, Alesandro Lazaric, and Michal Valko.