LGPRFeb 5, 2015

A Simple Expression for Mill's Ratio of the Student's $t$-Distribution

arXiv:1502.01632v1
Originality Synthesis-oriented
AI Analysis

This work addresses a theoretical gap in probability theory for researchers in statistics and machine learning, but it is incremental as it builds directly on existing conjectures.

The paper tackles the problem of deriving a simple expression for Mill's ratio of the Student's t-distribution, and uses it to prove a conjecture from a prior multi-armed bandit analysis, providing a theoretical result without specific numerical gains.

I show a simple expression of the Mill's ratio of the Student's t-Distribution. I use it to prove Conjecture 1 in P. Auer, N. Cesa-Bianchi, and P. Fischer. Finite-time analysis of the multiarmed bandit problem. Mach. Learn., 47(2-3):235--256, May 2002.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes