
TL;DR
This paper introduces a method to derive explicit upper bounds for tail probabilities of functions of random variables using the southwest boundary, applicable to homogeneous polynomials and matrix traces without independence assumptions.
Contribution
The authors develop a novel boundary-based approach for tail bounds that yields explicit formulas for complex functions like polynomials and matrix traces.
Findings
Derived explicit tail bounds for homogeneous polynomials of random variables.
Provided a closed-form tail bound for the trace of Schur multipliers on random matrices.
Bounded tail probabilities without requiring independence or dependence assumptions.
Abstract
We derive upper bounds for probabilities of the form using the southwest boundary (recently introduced in our previous work) , where is a reflection to the first quadrant. Under natural continuity, symmetry, and monotonicity assumptions on , this yields explicit and computable bounds of the form , where is the unique parameter at which the line intersects the southwest boundary. In particular, when is a homogeneous polynomial of degree (plus a constant ) and all tail bounds on the random variables are identical, the bound proves to the closed-form expression where are the coefficients of the monomials in . We then obtain an explicit…
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.
