Higher order elicitability and Osband's principle
Higher order elicitability and Osband's principle Page 1 The Annals of Statistics 2016, Vol. 44,
No. 4, 1680–1707 DOI: 10.1214/16-AOS1439 © Institute of Mathematical Statistics, 2016 …
No. 4, 1680–1707 DOI: 10.1214/16-AOS1439 © Institute of Mathematical Statistics, 2016 …
Elicitation and identification of properties
Abstract Properties of distributions are real-valued functionals such as the mean, quantile or
conditional value at risk. A property is elicitable if there exists a scoring function such that …
conditional value at risk. A property is elicitable if there exists a scoring function such that …
High-dimensional prediction for sequential decision making
We study the problem of making predictions of an adversarially chosen high-dimensional
state that are unbiased subject to an arbitrary collection of conditioning events, with the goal …
state that are unbiased subject to an arbitrary collection of conditioning events, with the goal …
Vector-valued property elicitation
R Frongillo, IA Kash - Conference on Learning Theory, 2015 - proceedings.mlr.press
The elicitation of a statistic, or property of a distribution, is the task of devising proper scoring
rules, equivalently proper losses, which incentivize an agent or algorithm to truthfully …
rules, equivalently proper losses, which incentivize an agent or algorithm to truthfully …
On conformal divergences and their population minimizers
Total Bregman divergences are a recent tweak of ordinary Bregman divergences originally
motivated by applications that required invariance by rotations. They have displayed …
motivated by applications that required invariance by rotations. They have displayed …
Comparing sequential forecasters
Consider two forecasters, each making a single prediction for a sequence of events over
time. We ask a relatively basic question: how might we compare these forecasters, either …
time. We ask a relatively basic question: how might we compare these forecasters, either …
[PDF][PDF] Elicitation and evaluation of statistical forecasts
NS Lambert - Preprint, 2011 - ai.stanford.edu
An expert has full or partial probabilistic information about a random state. The expert is
asked to make a prediction regarding a property of the state distribution, that is, to answer a …
asked to make a prediction regarding a property of the state distribution, that is, to answer a …
A general theory for structured prediction with smooth convex surrogates
In this work we provide a theoretical framework for structured prediction that generalizes the
existing theory of surrogate methods for binary and multiclass classification based on …
existing theory of surrogate methods for binary and multiclass classification based on …
Order-sensitivity and equivariance of scoring functions
The relative performance of competing point forecasts is usually measured in terms of loss
or scoring functions. It is widely accepted that these scoring function should be strictly …
or scoring functions. It is widely accepted that these scoring function should be strictly …
Elicitation complexity of statistical properties
RM Frongillo, IA Kash - Biometrika, 2021 - academic.oup.com
A property, or statistical functional, is said to be elicitable if it minimizes the expected loss for
some loss function. The study of which properties are elicitable sheds light on the …
some loss function. The study of which properties are elicitable sheds light on the …