Concentration inequalities under sub-Gaussian and sub-exponential conditions
Andreas Maurer · Massimiliano Pontil
Keywords:
Theory
2021 Poster
Abstract
We prove analogues of the popular bounded difference inequality (also called McDiarmid's inequality) for functions of independent random variables under sub-gaussian and sub-exponential conditions. Applied to vector-valued concentration and the method of Rademacher complexities these inequalities allow an easy extension of uniform convergence results for PCA and linear regression to the case potentially unbounded input- and output variables.
Video
Chat is not available.
Successful Page Load