Robust Testing in High-Dimensional Sparse Models
This addresses the challenge of robust statistical testing in high-dimensional sparse models for researchers in statistics and machine learning, but it is incremental as it extends prior observations in robust testing.
The paper tackles the problem of robustly testing the norm of a high-dimensional sparse signal vector under two observation models with arbitrary corruptions, showing that any algorithm requires sample complexities of n = Ω(s log(ed/s)) for the first model and n = Ω(min(s log d, 1/γ^4)) for the second, which are tight or significant increases under robustness constraints.
We consider the problem of robustly testing the norm of a high-dimensional sparse signal vector under two different observation models. In the first model, we are given $n$ i.i.d. samples from the distribution $\mathcal{N}\left(θ,I_d\right)$ (with unknown $θ$), of which a small fraction has been arbitrarily corrupted. Under the promise that $\|θ\|_0\le s$, we want to correctly distinguish whether $\|θ\|_2=0$ or $\|θ\|_2>γ$, for some input parameter $γ>0$. We show that any algorithm for this task requires $n=Ω\left(s\log\frac{ed}{s}\right)$ samples, which is tight up to logarithmic factors. We also extend our results to other common notions of sparsity, namely, $\|θ\|_q\le s$ for any $0 < q < 2$. In the second observation model that we consider, the data is generated according to a sparse linear regression model, where the covariates are i.i.d. Gaussian and the regression coefficient (signal) is known to be $s$-sparse. Here too we assume that an $ε$-fraction of the data is arbitrarily corrupted. We show that any algorithm that reliably tests the norm of the regression coefficient requires at least $n=Ω\left(\min(s\log d,{1}/{γ^4})\right)$ samples. Our results show that the complexity of testing in these two settings significantly increases under robustness constraints. This is in line with the recent observations made in robust mean testing and robust covariance testing.