Approximate Minimization of the Regularized Expected Error over Kernel Models
From MaRDI portal
Publication:3168992
DOI10.1287/moor.1080.0317zbMath1216.68135OpenAlexW2140677535MaRDI QIDQ3168992
Vera Kurková, Marcello Sanguineti
Publication date: 27 April 2011
Published in: Mathematics of Operations Research (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1287/moor.1080.0317
rates of convergencekernel methodsmodel complexityconvex functionalssuboptimal solutionsexpected error
Computational learning theory (68Q32) Programming in abstract spaces (90C48) Rate of convergence, degree of approximation (41A25) Applications of variational problems in infinite-dimensional spaces to the sciences (58E50)
Related Items
Learning with Boundary Conditions ⋮ On spectral windows in supervised learning from data ⋮ Suboptimal solutions to dynamic optimization problems via approximations of the policy functions ⋮ A meta-learning approach to the regularized learning -- case study: blood glucose prediction ⋮ Can dictionary-based computational models outperform the best linear ones? ⋮ Approximate dynamic programming for stochastic \(N\)-stage optimization with application to optimal consumption under uncertainty ⋮ New insights into Witsenhausen's counterexample ⋮ Functional optimization by variable-basis approximation schemes ⋮ Estimates of variation with respect to a set and applications to optimization problems ⋮ Estimates of the approximation error using Rademacher complexity: Learning vector-valued functions ⋮ Suboptimal Policies for Stochastic $$N$$-Stage Optimization: Accuracy Analysis and a Case Study from Optimal Consumption
Uses Software