Accelerating Machine Learning Algorithms with Adaptive Sampling

TL;DR

This paper introduces adaptive sampling techniques that replace costly subroutines in machine learning algorithms with randomized methods, significantly improving efficiency while maintaining accuracy.

Contribution

It proposes a novel approach of using randomized counterparts for computationally intensive parts, reducing runtime without sacrificing performance.

Findings

Randomized subroutines achieve near-original accuracy.

Adaptive sampling significantly speeds up algorithms.

Method applicable to large-scale datasets.

Abstract

The era of huge data necessitates highly efficient machine learning algorithms. Many common machine learning algorithms, however, rely on computationally intensive subroutines that are prohibitively expensive on large datasets. Oftentimes, existing techniques subsample the data or use other methods to improve computational efficiency, at the expense of incurring some approximation error. This thesis demonstrates that it is often sufficient, instead, to substitute computationally intensive subroutines with a special kind of randomized counterparts that results in almost no degradation in quality.