On the Bernstein-Hoeffding method
From MaRDI portal
Publication:4972049
Abstract: We show that the Bernstein-Hoeffding method can be employed to a larger class of generalized moments. This class includes the exponential moments whose properties play a key role in the proof of a well-known inequality of Wassily Hoeffding, for sums of independent and bounded random variables whose mean is assumed to be known. As a result we can generalise and improve upon this inequality. We show that Hoeffding's bound is optimal in a broader sense. Our approach allows to obtain "missing" factors in Hoeffding's inequality whose existence is motivated by the central limit theorem. The later result is a rather weaker version of a theorem that is due to Michel Talagrand. Using ideas from the theory of Bernstein polynomials, we show that the Bernstein-Hoeffding method can be adapted to case in which one has information on higher moments of the random variables. Moreover, we consider the performance of the method under additional information on the conditional distribution of the random variables and, finally, we show that the method reduces to Markov's inequality when employed to non-negative and unbounded random variables.
Recommendations
Cites work
- scientific article; zbMATH DE number 3126031 (Why is no real title available?)
- scientific article; zbMATH DE number 4170917 (Why is no real title available?)
- A Note on Hoeffding's Inequality
- A probability inequality for linear combinations of bounded random variables
- A refined Hoeffding's upper tail probability bound for sum of independent random variables
- A refinement of Hoeffding's inequality
- A remark on Bernstein, Prokhorov, Bennett, Hoeffding, and Talagrand inequalities
- Chernoff–Hoeffding Bounds for Applications with Limited Independence
- Exact inequalities for sums of asymmetric random variables, with applications
- Extremal properties of sums of Bernoulli random variables.
- Interpolation and approximation by polynomials
- On Hoeffding's inequalities.
- On inequalities for sums of bounded random variables
- On the Bennett-Hoeffding inequality
- Optimal Hoeffding-like inequalities under a symmetry assumption
- Probability Inequalities for Sums of Bounded Random Variables
- Probability Inequalities for Sums of Independent Random Variables
- Sharp large deviation results for sums of independent random variables
- Stochastic orders
- The missing factor in Hoeffding's inequalities
- Two refinements of the Chernoff bound for the sum of nonidentical Bernoulli random variables
Cited in
(14)- A modified Bernstein-technique for estimating noise-perturbed function values
- Hoeffding and Bernstein inequalities for weighted sums of exchangeable random variables
- Extremal properties of sums of Bernoulli random variables.
- Hoeffding's inequality for sums of dependent random variables
- A multivariate version of Hoeffding's inequality
- Bernstein-type bounds for beta distribution
- Faster Hoeffding racing: Bernstein races via jackknife estimates
- scientific article; zbMATH DE number 1419210 (Why is no real title available?)
- On the Bennett-Hoeffding inequality
- The missing factor in Hoeffding's inequalities
- On some extensions of Bernstein's inequality for self-adjoint operators
- A Bernstein-type inequality for functions of bounded interaction
- On Hoeffding and Bernstein type inequalities for sums of random variables in non-additive measure spaces and complete convergence
- Improving Hoeffding's inequality using higher moments information
This page was built for publication: On the Bernstein-Hoeffding method
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4972049)
