Open access
Date
2023Type
- Conference Paper
ETH Bibliography
yes
Altmetrics
Abstract
Consider the setting where a ρ-sparse Rademacher vector is planted in a random d-dimensional subspace of R n. A classical question is how to recover this planted vector given a random basis in this subspace. A recent result by Zadik et al. (2021) showed that the Lattice basis reduction algorithm can recover the planted vector when n ⩾ d + 1. Although the algorithm is not expected to tolerate inverse polynomial amount of noise, it is surprising because it was previously shown that recovery cannot be achieved by low degree polynomials when n ≪ ρ 2d 2 (Mao and Wein, 2021). A natural question is whether we can derive an Statistical Query (SQ) lower bound matching the previous low degree lower bound in Mao and Wein (2021). This will – imply that the SQ lower bound can be surpassed by lattice based algorithms; – predict the computational hardness when the planted vector is perturbed by inverse polynomial amount of noise. In this paper, we prove such an SQ lower bound. In particular, we show that super-polynomial number of VSTAT queries is needed to solve the easier statistical testing problem when n ≪ ρ 2d 2 and ρ ≫ √ 1 d . The most notable technique we used to derive the SQ lower bound is the almost equivalence relationship between SQ lower bound and low degree lower bound (Brennan et al., 2020; Mao and Wein, 2021) Show more
Permanent link
https://doi.org/10.3929/ethz-b-000647743Publication status
publishedExternal links
Book title
Proceedings of the 34th International Conference on Algorithmic Learning TheoryJournal / series
Proceedings of Machine Learning ResearchVolume
Pages / Article No.
Publisher
PMLREvent
Subject
Statistical query lower bound; Sparse recoveryOrganisational unit
09622 - Steurer, David / Steurer, David
Funding
815464 - Unified Theory of Efficient Optimization and Estimation (EC)
More
Show all metadata
ETH Bibliography
yes
Altmetrics