Sharp finite-sample concentration of independent variables
arXiv:2008.13293v53 citations
AI Analysis
This work addresses a foundational problem in probability theory and statistics, offering a general result with potential applications across machine learning and data science.
The authors extended Sanov's theorem on large deviations to provide matching concentration and anti-concentration bounds for i.i.d. random variables, applicable to any sample size with a short information-theoretic proof.
We show an extension of Sanov's theorem on large deviations, controlling the tail probabilities of i.i.d. random variables with matching concentration and anti-concentration bounds. This result has a general scope, applies to samples of any size, and has a short information-theoretic proof using elementary techniques.