mlsanityData to 14 Oct 2026

Sharp One-Dimensional Sub-Gaussian Comparison in Convex Order

arXiv 2604.26819 ↗First posted 29 Apr 2026math.PR cs.IT math.ITcited by 0

Not on the map. Why?

Abstract (arXiv)

We prove that any random variable X whose moment generating function is point-wise upper bounded by that of G ~ N(0,1) must be dominated by G/mathbbE[|G|] in convex order, meaning mathbbE[f(X)] ≤ mathbbE[f(G/mathbbE[|G|])] for all convex f. This is sharp as witnessed by X ~ Unif(-1,1) and f(x) = |x| .

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 1 of its 8 references that are in the map. First posted on arXiv 29 Apr 2026.

Builds on

1 of 8 references.

References · 1

  1. 2013Large Deviation Methods for Approximate Probabilistic Inferencecited by 12

Built on by

Not cited yet.