A variational formula on the Cram\'er function of series of independent random variables
Krzysztof Zajkowski

TL;DR
This paper generalizes a variational formula for the Cramér function from Rademacher series to a broader class of independent random variable series with coefficients in ^2, expanding its applicability.
Contribution
It extends the variational formula for the Crame9r function from Rademacher series to series of arbitrary independent random variables with ^2 coefficients.
Findings
Generalized the variational formula to a wider class of random variables.
Provided a new theoretical framework for analyzing large deviations.
Expanded the applicability of the Crame9r function analysis.
Abstract
In [11] it has been proved some variational formula on the Legendre-Fenchel transform of the cumulant generating function (the Cram\'er function) of Rademacher series with coefficients in the space . In this paper we show a generalization of this formula to series of a larger class of any independent random variables with coefficients that belong to the space .
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
