On the application of McDiarmid's inequality to complex systems

DOI10.1137/130933125zbMATH Open1378.60051arXiv1308.3304OpenAlexW2963432339MaRDI QIDQ5269861FDOQ5269861

Authors: Timothy C. Wallstrom 

Publication date: 28 June 2017

Published in: SIAM/ASA Journal on Uncertainty Quantification (Search for Journal in Brave)

Abstract: McDiarmid's inequality has recently been proposed as a tool for setting margin requirements for complex systems. If $F$ is the bounded output of a complex system, depending on a vector of $n$ bounded inputs, this inequality provides a bound $B_F(epsilon)$, such that the probability of a deviation exceeding $B_F(epsilon)$ is less than $epsilon$. I compare this bound with the absolute bound, based on the range of $F$. I show that when $n_{eff}$, the effective number of independent variates, is small, and when $epsilon$ is small, the absolute bound is smaller than $B_F(epsilon)$, while also providing a smaller probability of exceeding the bound, i.e., zero instead of $epsilon$. Thus, for $B_F(epsilon)$ to be useful, the number of inputs must be large, with a small dependence on any single input, which is consistent with the usual guidance for application of concentration-of-measure results. When the number of inputs is small, or when a small number of inputs account for much of the uncertainty, the absolute bounds will provide better results. The use of absolute bounds is equivalent to the original formulation of the method of Quantification of Margins and Uncertainties (QMU).

Full work available at URL: https://arxiv.org/abs/1308.3304

Recommendations

• On McDiarmid's concentration inequality
• Optimal uncertainty quantification for legacy data observations of Lipschitz functions
• scientific article; zbMATH DE number 1195776
• Advanced Lectures on Machine Learning
• Variations and extensions of the Gaussian concentration inequality, Part I

zbMATH Keywords

uncertainty quantificationcertificationconcentration of measuresmarginMcDiarmid inequalityquantification of margins and uncertainties

Mathematics Subject Classification ID

Large deviations (60F10) Inequalities; stochastic orderings (60E15)

Cites Work

• Title not available (Why is that?)
• Optimal uncertainty quantification
• Rigorous verification, validation, uncertainty quantification and certification through concentration-of-measure inequalities

Cited In (2)

• The Fisher-DisEn plane: a novel approach to distinguish different complex systems
• A not-so-fundamental limitation on studying complex systems with statistics: comment on Rabin (2011)

This page was built for publication: On the application of McDiarmid's inequality to complex systems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5269861)