Concentration inequalities for sub-additive functions using the entropy method
A function \(f\) of \(n\) variables is sub-additive if there exists a sequence of functions \(f_k\) of \(n-1\) variables such that for all \(x_1,\dots,x_n,\) \[ \sum^n_{k=1}f(x_1,\dots,x_n)-f_k(x_1,\dots,x_{k-1},x_{k+1},\dots,x_n)\leq f(x_1,\dots,x_n). \] A function of \(n\) independent random variables \(X_1,\dots,X_n\) is sub-additive if \(Z=f(X_1,\dots,X_n)\) is \(\sigma(X_1,\dots,X_n)\)-measurable, \(Z_k=f_k(X_1,\dots,X_{k-1},X_{k+1},\dots,X_n)\) is \(\sigma(X_1,\dots, X_{k-1},X_{k+1},\) \(\dots,X_n)\)-measurable for all \(k=1,2,\dots,n\) and the above inequality is satisfied almost surely. The difference \(Z-Z_k\) is called the increment of \(Z.\) Exponential concentration inequalities are obtained for sub-additive functions of independent random variables under weak conditions in the increments of these functions, like the existence of exponential moments for these increments. As a consequence of these general inequalities a refinement of Talagrand's inequality for empirical processes and new bounds for randomized processes associated to unbounded random variables are given. These results are obtained by further developing the entropy method introduced by Ledoux. For the entire collection see [Zbl 1024.00031].
- An exponential inequality for the distribution function of the kernel density estimator, with applications to adaptive estimation
- A statistical view of iterative methods for linear inverse problems
- Adaptation on the space of finite signed measures
- Concentration inequalities for separately convex functions
- Concentration around the mean for maxima of empirical processes
- Adaptive complexity regularization for linear inverse problems
- Iteratively reweighted _1-penalized robust regression
- Distributed adaptive Huber regression
- Concentration inequalities for suprema of unbounded empirical processes
- High-dimensional asymptotics of likelihood ratio tests in the Gaussian sequence model under convex constraints
- Berry-Esseen bounds for Chernoff-type nonstandard asymptotics in isotonic regression
- About the rate function in concentration inequalities for suprema of bounded empirical processes
- Global uniform risk bounds for wavelet deconvolution estimators
- On the Bennett-Hoeffding inequality
- Concentration inequalities and asymptotic results for ratio type empirical processes
- Concentration inequalities for sampling without replacement
- Local Rademacher complexities
- Exponential concentration inequalities for additive functionals of Markov chains
- Matrix completion via max-norm constrained optimization
- Penalized estimators for non linear inverse problems
- Theory of Classification: a Survey of Some Recent Advances
- Compressive sensing with redundant dictionaries and structured measurements
- Adaptive confidence sets in L^2
- About the rate function in Talagrand's inequality for empirical processes
- Thermodynamics and concentration
- Rates of contraction for posterior distributions in \(L^{r}\)-metrics, \(1 \leq r \leq \infty\)
- Adaptive confidence intervals for the tail coefficient in a wide second order class of Pareto models
- Random thresholds for linear model selection
- Variance-based regularization with convex objectives
- Histogram selection in non Gaussian regression
- Concentration inequalities for Poisson point processes with application to adaptive intensity estimation
- Statistical Analysis of Random Objects Via Metric Measure Laplacians
- High-dimensional composite quantile regression: optimal statistical guarantees and fast algorithms
- A Bernstein-type inequality for suprema of random processes with applications to model selection in non-Gaussian regression
- Adaptive estimation of a distribution function and its density in sup-norm loss by wavelet and spline projections
- Adaptive Huber trace regression with low-rank matrix parameter via nonconvex regularization
- Linear hypothesis testing in high-dimensional expected shortfall regression with heavy-tailed errors
- On the limitations of data-based price discrimination
- A high-dimensional Wilks phenomenon
- Concentration and moment inequalities for sums of independent heavy-tailed random matrices
This page was built for publication: Concentration inequalities for sub-additive functions using the entropy method
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4445180)
