English

Streaming Complexity of SVMs

Data Structures and Algorithms 2020-07-08 v1 Computational Complexity Computational Geometry Machine Learning

Abstract

We study the space complexity of solving the bias-regularized SVM problem in the streaming model. This is a classic supervised learning problem that has drawn lots of attention, including for developing fast algorithms for solving the problem approximately. One of the most widely used algorithms for approximately optimizing the SVM objective is Stochastic Gradient Descent (SGD), which requires only O(1λϵ)O(\frac{1}{\lambda\epsilon}) random samples, and which immediately yields a streaming algorithm that uses O(dλϵ)O(\frac{d}{\lambda\epsilon}) space. For related problems, better streaming algorithms are only known for smooth functions, unlike the SVM objective that we focus on in this work. We initiate an investigation of the space complexity for both finding an approximate optimum of this objective, and for the related ``point estimation'' problem of sketching the data set to evaluate the function value FλF_\lambda on any query (θ,b)(\theta, b). We show that, for both problems, for dimensions d=1,2d=1,2, one can obtain streaming algorithms with space polynomially smaller than 1λϵ\frac{1}{\lambda\epsilon}, which is the complexity of SGD for strongly convex functions like the bias-regularized SVM, and which is known to be tight in general, even for d=1d=1. We also prove polynomial lower bounds for both point estimation and optimization. In particular, for point estimation we obtain a tight bound of Θ(1/ϵ)\Theta(1/\sqrt{\epsilon}) for d=1d=1 and a nearly tight lower bound of Ω~(d/ϵ2)\widetilde{\Omega}(d/{\epsilon}^2) for d=Ω(log(1/ϵ))d = \Omega( \log(1/\epsilon)). Finally, for optimization, we prove a Ω(1/ϵ)\Omega(1/\sqrt{\epsilon}) lower bound for d=Ω(log(1/ϵ))d = \Omega( \log(1/\epsilon)), and show similar bounds when dd is constant.

Keywords

Cite

@article{arxiv.2007.03633,
  title  = {Streaming Complexity of SVMs},
  author = {Alexandr Andoni and Collin Burns and Yi Li and Sepideh Mahabadi and David P. Woodruff},
  journal= {arXiv preprint arXiv:2007.03633},
  year   = {2020}
}

Comments

APPROX 2020

R2 v1 2026-06-23T16:55:38.875Z