Approximation error bounds via Rademacher's complexity

MaRDI QIDQ3518954zbMATH OpenFDO

Authors Giorgio Gnecco, Marcello Sanguineti

Publication date 12 August 2008

Full work available at URL http://www.m-hikari.com/ams/ams-password-2008/ams-password1-4-2008/sanguinetiAMS1-4-2008.pdf

zbMATH Keywords

approximation errorcurse of dimensionalitymodel complexityRademacher's complexityTalagrand's inequalityunion boundsVC di- mension.

Mathematics Subject Classification ID

Approximation by rational functions (41A20) Nontrigonometric harmonic analysis (42C99) Geometry and structure of normed linear spaces (46B20) Learning and adaptive systems in artificial intelligence (68T05) Signal theory (characterization, reconstruction, filtering, etc.) (94A12)

Recommendations

• Estimates of the approximation error using Rademacher complexity: Learning vector-valued functions
• Generalization bounds for function approximation from scattered noisy data
• Local Rademacher complexities
• VC dimension, fat-shattering dimension, Rademacher averages, and their applications
• 10.1162/153244303321897690

Cited in

(17)

• Estimates of the approximation error using Rademacher complexity: Learning vector-valued functions
• Generalization bounds for function approximation from scattered noisy data
• The mechanism of additive composition
• Dynamic programming and value-function approximation in sequential decision problems: error analysis and numerical results
• Computational design of innovative mechanical metafilters via adaptive surrogate-based optimization
• Correlations of random classifiers on large data sets
• Complexity of approximating Hölder classes from information with varying Gaussian noise
• Error bounds for a near-minimax approximation
• Approximate dynamic programming for stochastic \(N\)-stage optimization with application to optimal consumption under uncertainty
• An improved probability bound for the approximate S-lemma
• A Vector-Contraction Inequality for Rademacher Complexities
• Suboptimal Policies for Stochastic N-Stage Optimization: Accuracy Analysis and a Case Study from Optimal Consumption
• Foundations of support constraint machines
• Suboptimal solutions to dynamic optimization problems via approximations of the policy functions
• Design of experiments for the calibration of history-dependent models via deep reinforcement learning and an enhanced Kalman filter
• Improved accuracy of an analytical approximation for option pricing under stochastic volatility models using deep learning techniques
• Finite element operator network for solving elliptic-type parametric PDEs

This page was built for publication: Approximation error bounds via Rademacher's complexity

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3518954)