Pith. sign in

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

arxiv 1306.2872 v3 pith:TMXOU5FL submitted 2013-06-12 math.PR

classification math.PR
keywords randomconcentrationinequalitysub-gaussianhanson-wrightvectorsbounddeduce
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Microscopic Side Information Controls Ordered Hayden--Preskill Recovery

    quant-ph 2026-07 conditional novelty 7.0 of 10

    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.

  2. Shrinkage to Infinity: Reducing Test Error by Inflating the Minimum Norm Interpolator in Linear Models

    math.ST 2025-10 unverdicted novelty 7.0 of 10

    Inflating the min-norm interpolator by a factor >1 reduces generalization error in linear regression with anisotropic covariances when d/n diverges to infinity.

  3. Provable Non-Convex Euclidean Distance Matrix Completion: Geometry, Reconstruction, and Robustness

    math.OC 2025-07 unverdicted novelty 6.0 of 10

    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.

  4. Collaborative Prediction: To Join or To Disjoin Datasets

    stat.ML 2025-06 conditional novelty 6.0 of 10

    A data-driven rule decides when to merge or keep separate datasets for linear prediction, with a high-probability guarantee under Gaussian linear models.

Pith tools