Concentration of weakly dependent Banach-valued sums and applications to kernel learning methods

12/05/2017
by   Gilles Blanchard, et al.
0

We obtain a new Bernstein-type inequality for sums of Banach-valued random variables satisfying a weak dependence assumption of general type and under certain smoothness assumptions of the underlying Banach norm. We use this inequality in order to investigate in asymptotical regime the error upper bounds for the broad family of spectral regularization methods for reproducing kernel decision rules, when trained on a sample coming from a τ-mixing process.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/23/2018

An Exact Upper Bound on the L^p Lebesgue Constant and The ∞-Rényi Entropy Power Inequality for Integer Valued Random Variables

In this paper, we proved an exact asymptotically sharp upper bound of th...
research
11/23/2022

On the links between Stein transforms and concentration inequalities for dependent random variables

In this paper, we explore some links between transforms derived by Stein...
research
01/02/2021

New-Type Hoeffding's Inequalities and Application in Tail Bounds

It is well known that Hoeffding's inequality has a lot of applications i...
research
09/11/2023

Concentration of Submodular Functions Under Negative Dependence

We study the question of whether submodular functions of random variable...
research
02/09/2021

The Multiplicative Version of Azuma's Inequality, with an Application to Contention Analysis

Azuma's inequality is a tool for proving concentration bounds on random ...
research
09/06/2018

A note on concentration inequality for vector-valued martingales with weak exponential-type tails

We present novel martingale concentration inequalities for martingale di...
research
08/24/2022

An Improved Bernstein-type Inequality for C-Mixing-type Processes and Its Application to Kernel Smoothing

There are many processes, particularly dynamic systems, that cannot be d...

Please sign up or login with your details

Forgot password? Click here to reset