Equivalence of concentration inequalities for linear and non-linear functions
نویسنده
چکیده
We consider a random variable X that takes values in a (possibly infinite-dimensional) topological vector space X . We show that, with respect to an appropriate “normal distance” on X , concentration inequalities for linear and non-linear functions ofX are equivalent. This normal distance corresponds naturally to the concentration rate in classical concentration results such as Gaussian concentration and concentration on the Euclidean and Hamming cubes. Under suitable assumptions on the roundness of the sets of interest, the concentration inequalities so obtained are asymptotically optimal in the high-dimensional limit.
منابع مشابه
Modified homotopy method to solve non-linear integral equations
In this article we decide to define a modified homotopy perturbation for solving non-linear integral equations. Almost, all of the papers that was presented to solve non-linear problems by the homotopy method, they used from two non-linear and linear operators. But we convert a non-linear problem to two suitable non-linear operators also we use from appropriate bases functions such as Legendre ...
متن کاملLinear optimization on Hamacher-fuzzy relational inequalities
In this paper, optimization of a linear objective function with fuzzy relational inequality constraints is investigated where the feasible region is formed as the intersection of two inequality fuzzy systems and Hamacher family of t-norms is considered as fuzzy composition. Hamacher family of t-norms is a parametric family of continuous strict t-norms, whose members are decreasing functions of ...
متن کاملNon Uniform Rational B Spline (NURBS) Based Non-Linear Analysis of Straight Beams with Mixed Formulations
Displacement finite element models of various beam theories have been developed traditionally using conventional finite element basis functions (i.e., cubic Hermite, equi-spaced Lagrange interpolation functions, or spectral/hp Legendre functions). Various finite element models of beams differ from each other in the choice of the interpolation functions used for the transverse deflection w, tota...
متن کاملApplication of Non-Linear Functions at Distribution of Output SINR Gaussian Interference Channels
We have examined the convergence behavior of the LSCMA in some simple environments. Algorithms such as Multi¬ Target CMA, Multistage CMA, and Iterative Least Squares with Projection can be used for this purpose. The results presented here can form a basis for analysis of these multi-signal extraction techniques. Clearly, the variance and distribution of output SINR obtained with the LSCMA is al...
متن کاملTwo New Non-AFR Criteria for Depicting Strength Differential Effect (SDE) in Anisotropic Sheet Metals
The issue of pressure sensitivity of anisotropic sheet metals is investigated with introducing two new non-AFR criteria which are called here linear and non-Linear pressure sensitive criteria. The yield and plastic potential functions of these criteria are calibrated with directional tensile/compressive yield stresses and directional tensile Lankford coefficients, respectively. To determine unk...
متن کامل