Testing Halfspaces over Rotation-Invariant Distributions

10/31/2018
by   Nathaniel Harms, et al.
0

We present an algorithm for testing halfspaces over arbitrary, unknown rotation-invariant distributions. Using Õ(√(n)ϵ^-7) random examples of an unknown function f, the algorithm determines with high probability whether f is of the form f(x) = sign(∑_i w_ix_i-t) or is ϵ-far from all such functions. This sample size is significantly smaller than the well-known requirement of Ω(n) samples for learning halfspaces, and known lower bounds imply that our sample size is optimal (in its dependence on n) up to logarithmic factors. The algorithm is distribution-free in the sense that it requires no knowledge of the distribution aside from the promise of rotation invariance. To prove the correctness of this algorithm we present a theorem relating the distance between a function and a halfspace to the distance between their centers of mass, that applies to arbitrary distributions.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/17/2019

Testing Properties of Multiple Distributions with Few Samples

We propose a new setting for testing properties of distributions while r...
research
02/09/2020

Monotone probability distributions over the Boolean cube can be learned with sublinear samples

A probability distribution over the Boolean cube is monotone if flipping...
research
12/09/2020

Objective Bayesian approach to the Jeffreys-Lindley paradox

We consider the Jeffreys-Lindley paradox from an objective Bayesian pers...
research
10/19/2021

Exploring the Gap between Tolerant and Non-tolerant Distribution Testing

The framework of distribution testing is currently ubiquitous in the fie...
research
05/01/2020

Distributions of restricted rotation distances

Rotation distances measure the differences in structure between rooted o...
research
05/02/2023

Sample-based distance-approximation for subsequence-freeness

In this work, we study the problem of approximating the distance to subs...
research
10/28/2019

Testing Equivalence of Clustering

In this paper, we test whether two datasets share a common clustering st...

Please sign up or login with your details

Forgot password? Click here to reset