Robust testing of low-dimensional functions

04/24/2020
by   Anindya De, et al.
0

A natural problem in high-dimensional inference is to decide if a classifier f:ℝ^n → [-1,1] depends on a small number of linear directions of its input data. Call a function g: ℝ^n → [-1,1], a linear k-junta if it is completely determined by some k-dimensional subspace of the input space. A recent work of the authors showed that linear k-juntas are testable. Thus there exists an algorithm to distinguish between: 1. f: ℝ^n →{-1,1} which is a linear k-junta with surface area s, 2. f is ϵ-far from any linear k-junta, where the query complexity of the algorithm is independent of the ambient dimension n. Following the surge of interest in noise-tolerant property testing, in this paper we prove a noise-tolerant (or robust) version of this result. Namely, we give an algorithm which given any c>0, ϵ>0, distinguishes between 1. f: ℝ^n →{-1,1} has correlation at least c with some linear k-junta with surface area s. 2. f has correlation at most c-ϵ with any linear k-junta. Our query complexity is qualitatively the same, i.e., remains independent of n and is polynomially dependent on k. A major motivation for studying Linear Junta Testing come from statistical models where it is crucial to allow noise. In the language of model compression, our results show statistical models can be "compressed" in query complexity that depends only on the size of the desired compression, when the compression is a linear Junta.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/26/2018

Is your function low-dimensional?

We study the problem of testing if a function depends on a small number ...
research
11/03/2019

Testing noisy linear functions for sparsity

We consider the following basic inference problem: there is an unknown h...
research
06/26/2018

Is your data low-dimensional?

We study the problem of testing if a function depends on a small number ...
research
04/26/2022

Tolerant Bipartiteness Testing in Dense Graphs

Bipartite testing has been a central problem in the area of property tes...
research
08/02/2012

Efficient Point-to-Subspace Query in ℓ^1 with Application to Robust Object Instance Recognition

Motivated by vision tasks such as robust face and object recognition, we...
research
04/08/2019

Junta correlation is testable

The problem of tolerant junta testing is a natural and challenging probl...
research
11/15/2019

Testing linear-invariant properties

We prove that all linear-invariant, linear-subspace hereditary, locally ...

Please sign up or login with your details

Forgot password? Click here to reset