High‐dimensional Statistics: A Non‐asymptotic Viewpoint, Martin J.Wainwright, Cambridge University Press, 2019, xvii 552 pages, £57.99, hardback ISBN: 978‐1‐1084‐9802‐9

1,625 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

The Right Complexity Measure in Locally Private Estimation: It is not the Fisher Information (2018, methodology): “We begin with a result essentially due to Yu [56, Lemma 1] (see also [52]), known as the generalized Le Cam’s method.”
Policy Learning With Observational Data (2017, methodology): “Linear Rules The VC-dimension of the class of linear decision rules is (Wainwright, 2019, p. 116 Thus, our approach applies to linear decision rules in dimension p n ≤ n β for some β < 1 / 2.”
Time-uniform Chernoff bounds via nonnegative supermartingales (2018, background): “This argument is adapted from Wainwright (2017), though the idea originates in Oliveira (2010b).”
Adversarially Robust Generalization Just Requires More Unlabeled Data (2019, methodology): “(Concentration of covariance estimation, see Corollary 8.7 in [42]).”
AUTO-ENCODING VARIATIONAL BAYES (2020, positive): “From the invariance properties of Gaussian distributions [31], our next lemma gives concentration bounds for the log-ratio statistics under the posterior.”
Convex Formulations for Fair Principal Component Analysis (2018, neutral): “Recall that V ( F c ) = d +1 (Shorack and Wellner 2009), and that V ( F v ) = d + 1 (Wainwright 2017).”