This paper considers least squares estimators for regression
problems over convex, uniformly bounded, uniformly Lipschitz function
classes minimizing the empirical risk over max-affine functions
(the maximum of finitely many affine functions).
Based on new results on nonlinear nonparametric regression
and on the approximation accuracy of max-affine functions,
these estimators are proved to achieve the optimal rate of
convergence up to logarithmic factors.
Preliminary experiments indicate that a simple randomized approximation
to the optimal estimator is competitive with state-of-the-art alternatives.
%0 Conference Paper
%1 BaGySz15
%A Balázs, G.
%A György, A.
%A Szepesvári, Cs.
%B AISTATS
%D 2015
%K convex nonparametrics, regression regression,
%P 56--64
%T Near-optimal max-affine estimators for convex regression
%X This paper considers least squares estimators for regression
problems over convex, uniformly bounded, uniformly Lipschitz function
classes minimizing the empirical risk over max-affine functions
(the maximum of finitely many affine functions).
Based on new results on nonlinear nonparametric regression
and on the approximation accuracy of max-affine functions,
these estimators are proved to achieve the optimal rate of
convergence up to logarithmic factors.
Preliminary experiments indicate that a simple randomized approximation
to the optimal estimator is competitive with state-of-the-art alternatives.
@inproceedings{BaGySz15,
abstract = { This paper considers least squares estimators for regression
problems over convex, uniformly bounded, uniformly Lipschitz function
classes minimizing the empirical risk over max-affine functions
(the maximum of finitely many affine functions).
Based on new results on nonlinear nonparametric regression
and on the approximation accuracy of max-affine functions,
these estimators are proved to achieve the optimal rate of
convergence up to logarithmic factors.
Preliminary experiments indicate that a simple randomized approximation
to the optimal estimator is competitive with state-of-the-art alternatives.
},
added-at = {2020-03-17T03:03:01.000+0100},
author = {Bal{\'a}zs, G. and Gy{\"o}rgy, A. and Szepesv{\'a}ri, {Cs}.},
biburl = {https://www.bibsonomy.org/bibtex/2d7178135f7e553225c62c5dd1201afa6/csaba},
booktitle = {AISTATS},
date-added = {2015-01-27 08:03:13 +0000},
date-modified = {2015-08-02 01:02:30 +0000},
interhash = {85f460c93bdd13de467e08ec9328deb7},
intrahash = {d7178135f7e553225c62c5dd1201afa6},
keywords = {convex nonparametrics, regression regression,},
pages = {56--64},
pdf = {papers/AISTAT15-cvxreg.pdf},
timestamp = {2020-03-17T03:03:01.000+0100},
title = {Near-optimal max-affine estimators for convex regression},
year = 2015
}