Exploiting the Structure: Stochastic Gradient Methods Using Raw Clusters

Abstract

The amount of data available in the world is growing faster than our ability to deal with it. However, if we take advantage of the internal \emph{structure}, data may become much smaller for machine learning purposes. In this paper we focus on one of the fundamental machine learning tasks, empirical risk minimization (ERM), and provide faster algorithms with the help from the clustering structure of the data. We introduce a simple notion of raw clustering that can be efficiently computed from the data, and propose two algorithms based on clustering information. Our accelerated algorithm ClusterACDM is built on a novel Haar transformation applied to the dual space of the ERM problem, and our variance-reduction based algorithm ClusterSVRG introduces a new gradient estimator using clustering. Our algorithms outperform their classical counterparts ACDM and SVRG respectively.

Cited by in corpus (6)

• Even Faster Accelerated Coordinate Descent Using Non-Uniform Sampling
• Optimal Hashing-based Time-Space Trade-offs for Approximate Near Neighbors
• Lower Bounds on Time-Space Trade-Offs for Approximate Near Neighbors
• Accelerating Stochastic Gradient Descent Using Antithetic Sampling
• The Lingering of Gradients: Theory and Applications
• Approximate Inference via Clustering