2000 character limit reached
Sharp finite-sample concentration of independent variables (2008.13293v5)
Published 30 Aug 2020 in cs.LG, cs.IT, math.IT, math.PR, and stat.ML
Abstract: 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.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.