REVIEW 2 cited by
Optimal Spectral Recovery of a Planted Vector in a Subspace
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
abstract
Recovering a planted vector $v$ in an $n$-dimensional random subspace of $\mathbb{R}^N$ is a generic task related to many problems in machine learning and statistics, such as dictionary learning, subspace recovery, principal component analysis, and non-Gaussian component analysis. In this work, we study computationally efficient estimation and detection of a planted vector $v$ whose $\ell_4$ norm differs from that of a Gaussian vector with the same $\ell_2$ norm. For instance, in the special case where $v$ is an $N \rho$-sparse vector with Bernoulli-Gaussian or Bernoulli-Rademacher entries, our results include the following: (1) We give an improved analysis of a slight variant of the spectral method proposed by Hopkins, Schramm, Shi, and Steurer (2016), showing that it approximately recovers $v$ with high probability in the regime $n \rho \ll \sqrt{N}$. This condition subsumes the conditions $\rho \ll 1/\sqrt{n}$ or $n \sqrt{\rho} \lesssim \sqrt{N}$ required by previous work up to polylogarithmic factors. We achieve $\ell_\infty$ error bounds for the spectral estimator via a leave-one-out analysis, from which it follows that a simple thresholding procedure exactly recovers $v$ with Bernoulli-Rademacher entries, even in the dense case $\rho = 1$. (2) We study the associated detection problem and show that in the regime $n \rho \gg \sqrt{N}$, any spectral method from a large class (and more generally, any low-degree polynomial of the input) fails to detect the planted vector. This matches the condition for recovery and offers evidence that no polynomial-time algorithm can succeed in recovering a Bernoulli-Gaussian vector $v$ when $n \rho \gg \sqrt{N}$.
Forward citations
Cited by 2 Pith papers
-
SoS Certificates for Sparse Singular Values and Their Applications: Robust Statistics, Subspace Distortion, and More
New SoS certificates certify nontrivial sparse singular values of random Gaussian and subgaussian matrices whenever n ≫ η²d^(2+ε), nearly matching low-degree and SQ lower bounds and yielding near-optimal robust estima...
-
Recovering Imbalanced Clusters via Gradient-Based Projection Pursuit
Imbalanced clusters are provably easier to recover than balanced ones, and a two-step gradient ascent algorithm with normalized-sample initialization achieves Θ~(d²p²) sample complexity.
Discussion (0). Continue with ORCID to comment.