Skip to main content
http -> https (the question was bumped anyway)
Source Link
Martin Sleziak
  • 4.7k
  • 4
  • 35
  • 40

I can provide you concentration inequality around the mean, in particular the decay is exponential et reflects the correct size of the variance. It is important to notice that Classical concentration inequality for Lipschitz functions can not be applied.

As a reference see :

http://perso.math.univ-toulouse.fr/ktanguy/files/2012/04/Article-3-brouillon.pdfhttps://perso.math.univ-toulouse.fr/ktanguy/files/2012/04/Article-3-brouillon.pdf

Kevin Tanguy

I can provide you concentration inequality around the mean, in particular the decay is exponential et reflects the correct size of the variance. It is important to notice that Classical concentration inequality for Lipschitz functions can not be applied.

As a reference see :

http://perso.math.univ-toulouse.fr/ktanguy/files/2012/04/Article-3-brouillon.pdf

Kevin Tanguy

I can provide you concentration inequality around the mean, in particular the decay is exponential et reflects the correct size of the variance. It is important to notice that Classical concentration inequality for Lipschitz functions can not be applied.

As a reference see :

https://perso.math.univ-toulouse.fr/ktanguy/files/2012/04/Article-3-brouillon.pdf

Kevin Tanguy

Source Link

I can provide you concentration inequality around the mean, in particular the decay is exponential et reflects the correct size of the variance. It is important to notice that Classical concentration inequality for Lipschitz functions can not be applied.

As a reference see :

http://perso.math.univ-toulouse.fr/ktanguy/files/2012/04/Article-3-brouillon.pdf

Kevin Tanguy