REVIEW 4 cited by
Hanson-Wright inequality and sub-gaussian concentration
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
read the original abstract
In this expository note, we give a modern proof of Hanson-Wright inequality for quadratic forms in sub-gaussian random variables. We deduce a useful concentration inequality for sub-gaussian random vectors. Two examples are given to illustrate these results: a concentration of distances between random vectors and subspaces, and a bound on the norms of products of random and deterministic matrices.
Forward citations
Cited by 4 Pith papers
-
Microscopic Side Information Controls Ordered Hayden--Preskill Recovery
Without microscopic position labels, Hayden–Preskill recovery of a fixed diary requires Θ(n^{2/3}) output qubits; coarse block labels reduce this to n^{2/3}B^{-1/3} or n/B.
-
Shrinkage to Infinity: Reducing Test Error by Inflating the Minimum Norm Interpolator in Linear Models
Inflating the min-norm interpolator by a factor >1 reduces generalization error in linear regression with anisotropic covariances when d/n diverges to infinity.
-
Provable Non-Convex Euclidean Distance Matrix Completion: Geometry, Reconstruction, and Robustness
Riemannian gradient descent on rank-r Gram matrices for EDMC achieves linear convergence with high probability for sampling probability p ≥ O(ν² r² log(n)/n) and a hard-thresholding initialization under a weaker rate.
-
Collaborative Prediction: To Join or To Disjoin Datasets
A data-driven rule decides when to merge or keep separate datasets for linear prediction, with a high-probability guarantee under Gaussian linear models.
Discussion (0). Continue with ORCID to comment.