Sub-Poisson distributions: Concentration inequalities, optimal variance proxies, and closure properties
By: Lasse Leskelä, Ian Välimaa
Potential Business Impact:
Makes math tools work better for predicting random events.
We introduce a nonasymptotic framework for sub-Poisson distributions with moment generating function dominated by that of a Poisson distribution. At its core is a new notion of optimal sub-Poisson variance proxy, analogous to the variance parameter in the sub-Gaussian setting. This framework allows us to derive a Bennett-type concentration inequality without boundedness assumptions and to show that the sub-Poisson property is closed under key operations including independent sums and convex combinations, but not under all linear operations such as scalar multiplication. We derive bounds relating the sub-Poisson variance proxy to sub-Gaussian and sub-exponential Orlicz norms. Taken together, these results unify the treatment of Bernoulli and Poisson random variables and their signed versions in their natural tail regime.
Similar Papers
A variational approach to dimension-free self-normalized concentration
Probability
Makes math work better for smart computer learning.
Optimal sub-Gaussian variance proxy for 3-mass distributions
Statistics Theory
Makes math tools better for guessing random events.
Concentration inequalities for strong laws and laws of the iterated logarithm
Probability
Makes math rules for guessing more accurate.