Linear Functions to the Extended Reals

02/18/2021
by   Bo Waggoner, et al.
0

This note investigates functions from ℝ^d to ℝ∪{±∞} that satisfy axioms of linearity wherever allowed by extended-value arithmetic. They have a nontrivial structure defined inductively on d, and unlike finite linear functions, they require Ω(d^2) parameters to uniquely identify. In particular they can capture vertical tangent planes to epigraphs: a function (never -∞) is convex if and only if it has an extended-valued subgradient at every point in its effective domain, if and only if it is the supremum of a family of "affine extended" functions. These results are applied to the well-known characterization of proper scoring rules, for the finite-dimensional case: it is carefully and rigorously extended here to a more constructive form. In particular it is investigated when proper scoring rules can be constructed from a given convex function.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/16/2019

A new example for a proper scoring rule

We give a new example for a proper scoring rule motivated by the form of...
research
05/07/2021

An Objective Prior from a Scoring Rule

In this paper we introduce a novel objective prior distribution levering...
research
06/19/2018

Properization

Scoring rules serve to quantify predictive performance. A scoring rule i...
research
04/08/2013

The PAV algorithm optimizes binary proper scoring rules

There has been much recent interest in application of the pool-adjacent-...
research
08/22/2018

Calibration Scoring Rules for Practical Prediction Training

In situations where forecasters are scored on the quality of their proba...
research
05/01/2023

Proper Scoring Rules for Survival Analysis

Survival analysis is the problem of estimating probability distributions...

Please sign up or login with your details

Forgot password? Click here to reset