On the optimality of the empirical risk minimization procedure for the Convex Aggregation problem
نویسندگان
چکیده
We study the performance of empirical risk minimization (ERM), with respect to the quadratic risk, in the context of convex aggregation, in which one wants to construct a procedure whose risk is as close as possible to the best function in the convex hull of an arbitrary finite class F . We show that ERM performed in the convex hull of F is an optimal aggregation procedure for the convex aggregation problem. We also show that if this procedure is used for the problem of model selection aggregation, in which one wants to mimic the performance of the best function in F itself, then its rate is the same as the one achieved for the convex aggregation problem, and thus is far from optimal. These results are obtained in deviation and are sharp up to logarithmic factors. (Résumé en Français: Nous étudions les performances de la procédure de minimisation du risque empirique, par rapport au risque quadratique, pour le problème d’agrégation convexe. Dans ce problème, on souhaite construire des procédures dont le risque est aussi proche que possible du risque du meilleur élément dans l’enveloppe convexe d’une classe finie F de fonctions. Nous prouvons que la procédure obtenue par minimisation du risque empirique sur la coque convexe de F est une procédure optimale pour le problème d’aggrégation convexe. Nous prouvons aussi que si cette procédure est utilisée pour le problème d’agrégation en sélection de modèle, pour lequel on souhaite imiter le meilleur dans F , alors le résidue d’agrégation est le même que celui obtenue pour le problème d’agrégation convexe. Cette procédure est donc loin d’être optimale pour le problème d’agrégation en sélection de modèle. Ces résultats sont obtenus en déviation et sont optimaux à des facteurs logarithmiques prés.) CNRS, LAMA, Université Paris-Est Marne-la-vallée, 77454 France. Department of Mathematics, Technion, I.I.T, Haifa 32000, Israel. Part of this research was supported by the Centre for Mathematics and its Applications, The Australian National University, Canberra, ACT 0200, Australia, by an Australian Research Council Discovery grant DP0559465 and by the European Community’s Seventh Framework Programme (FP7/2007-2013), ERC grant agreement 203134. Email: [email protected] Email: [email protected]
منابع مشابه
Empirical risk minimization is optimal for the convex aggregation problem
Let F be a finite model of cardinality M and denote by conv(F ) its convex hull. The problem of convex aggregation is to construct a procedure having a risk as close as possible to the minimal risk over conv(F ). Consider the bounded regression model with respect to the squared risk denoted by R(·). If f̂ ERM-C n denotes the empirical risk minimization procedure over conv(F ), then we prove that...
متن کاملAggregation via Empirical Risk Minimization
Given a finite set F of estimators, the problem of aggregation is to construct a new estimator whose risk is as close as possible to the risk of the best estimator in F . It was conjectured that empirical minimization performed in the convex hull of F is an optimal aggregation method, but we show that this conjecture is false. Despite that, we prove that empirical minimization in the convex hul...
متن کاملAggregation versus Empirical Risk Minimization
Abstract Given a finite set F of estimators, the problem of aggregation is to construct a new estimator that has a risk as close as possible to the risk of the best estimator in F . It was conjectured that empirical minimization performed in the convex hull of F is an optimal aggregation method, but we show that this conjecture is false. Despite that, we prove that empirical minimization in the...
متن کامل[hal-00736203, v1] Empirical risk minimization is optimal for the convex aggregation problem
Let F be a finite model of cardinality M and denote by conv(F ) its convex hull. The problem of convex aggregation is to construct a procedure having a risk as close as possible to the minimal risk over conv(F ). Consider the bounded regression model with respect to the squared risk denoted by R(·). If f̂ n denotes the empirical risk minimization procedure over conv(F ) then we prove that for an...
متن کاملOptimality and Duality for an Efficient Solution of Multiobjective Nonlinear Fractional Programming Problem Involving Semilocally Convex Functions
In this paper, the problem under consideration is multiobjective non-linear fractional programming problem involving semilocally convex and related functions. We have discussed the interrelation between the solution sets involving properly efficient solutions of multiobjective fractional programming and corresponding scalar fractional programming problem. Necessary and sufficient optimality...
متن کامل