DeepAI AI Chat
Log In Sign Up

Streaming Complexity of SVMs

by   Alexandr Andoni, et al.

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(1/λϵ) random samples, and which immediately yields a streaming algorithm that uses O(d/λϵ) 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 F_λ on any query (θ, b). We show that, for both problems, for dimensions d=1,2, one can obtain streaming algorithms with space polynomially smaller than 1/λϵ, 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=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)) for d=1 and a nearly tight lower bound of Ω(d/ϵ^2) for d = Ω( log(1/ϵ)). Finally, for optimization, we prove a Ω(1/√(ϵ)) lower bound for d = Ω( log(1/ϵ)), and show similar bounds when d is constant.


page 1

page 2

page 3

page 4


Tight Space Lower Bound for Pseudo-Deterministic Approximate Counting

We investigate one of the most basic problems in streaming algorithms: a...

Space Lower Bounds for Graph Stream Problems

This work concerns with proving space lower bounds for graph problems in...

Streaming and Sketching Complexity of CSPs: A survey

In this survey we describe progress over the last decade or so in unders...

How Good is SGD with Random Shuffling?

We study the performance of stochastic gradient descent (SGD) on smooth ...

A tight lower bound on non-adaptive group testing estimation

Efficiently counting or detecting defective items is a crucial task in v...

Streaming Algorithms for Planar Convex Hulls

Many classical algorithms are known for computing the convex hull of a s...

On the amortized complexity of approximate counting

Naively storing a counter up to value n would require Ω(log n) bits of m...