Bracketing numbers of convex and <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" display="inline" id="d1e25" altimg="si4.svg"><mml:mi>m</mml:mi></mml:math>-monotone functions on polytopes

Doss, Charles R.

doi:10.1016/j.jat.2020.105425

Cited by 2 publications

(1 citation statement)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…for affine functions f 0 under the ℓ Pn pseudometric. This result is different from existing metric entropy results in [9,15,20,25,26] for convex functions in that it deals with the discrete ℓ Pn pseudometric while all existing results deal with continuous L p metrics. Also the constraint ℓ Pn (f, f 0 ) ≤ t on the convex functions in the above class is comparatively weak.…”

Section: Introductioncontrasting

confidence: 73%

Convex Regression in Multidimensions: Suboptimality of Least Squares Estimators

Kur,

Gao,

Guntuboyina

et al. 2020

Preprint

View full text Add to dashboard Cite

The least squares estimator (LSE) is shown to be suboptimal in squared error loss in the usual nonparametric regression model with Gaussian errors for d ≥ 5 for each of the following families of functions: (i) convex functions supported on a polytope (in fixed design), (ii) bounded convex functions supported on a polytope (in random design), and (iii) convex Lipschitz functions supported on any convex domain (in random design). For each of these families, the risk of the LSE is proved to be of the order n −2/d (up to logarithmic factors) while the minimax risk is n −4/(d+4) , for d ≥ 5. In addition, the first rate of convergence results (worst case and adaptive) for the full convex LSE are established for polytopal domains for all d ≥ 1. Some new metric entropy results for convex functions are also proved which are of independent interest.

show abstract