Upper bounds on product and multiplier empirical processes

By Shahar Mendelson. 2014

88 citations recorded by the source corpus.

We study two empirical processes of special structure: firstly, the centred multiplier process indexed by a class F, f→|∑i=1N(ξif(Xi)−Eξf)|, where the i.i.d. multipliers (ξi)i=1N need not be independent of (Xi)i=1N, and secondly, (f,h)→|∑i=1N(f(Xi)h(Xi)−Efh)|, the centred product process indexed by the classes F and H.

Subfields: Mathematical Physics, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/e1b1f2eb6761aac01d9986a980b40c21b7bcc2c2

How researchers see this paper

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

In Mathematical Physics

In Statistics and Probability

Citations in the corpus

Slope meets Lasso: Improved oracle bounds and optimality (2016, unknown): “12 in [20]) that for all u > 0, with probability at least 1− 2 exp(−C2 min(u(2), u √ n)), sup v∈T ∣”
Convergence rates of least squares regression estimators with heavy-tailed errors (2017, methodology): “The bounds in [45] use techniques from generic chaining [58], and work particularly well for “sub-Gaussian classes” (defined in [45]).”
Robust covariance estimation under $L_{4}-L_{2}$ norm equivalence (2018, background): “, [7, 8, 9]), mainly using chaining methods.”
Regularization, sparse recovery, and median-of-means tournaments (2017, background): “ on these complexity parameters, even for the lasso, is nontrivial, and a rich mathematical theory has been developed just for that goal (see, e.g., the books [7, 16, 2], and for more recent results, [13]). We study the parameters in question for ℓ1-regularized linear regression (lasso) and also for”
Risk minimization by median-of-means tournaments (2016, background): “Although it is formulated in R n , it holds in a far more general context (see [33]).”