We provide a novel reduction from swap-regret minimization to external-regret minimization,
which improves upon the classical reductions of Blum-Mansour and Stoltz-Lugosi in that it …

A recent line of work has shown a surprising connection between multicalibration, a multi-
group fairness notion, and omniprediction, a learning paradigm that provides simultaneous …

Consider the supervised learning setting where the goal is to learn to predict labels $\mathbf
y $ given points $\mathbf x $ from a distribution. An\textit {omnipredictor} for a class …

We study a sequential binary prediction setting where the forecaster is evaluated in terms of
the calibration distance, which is defined as the $ L_1 $ distance between the predicted …

How should an expert send forecasts to maximize her utility subject to passing a calibration
test? We consider a dynamic game where an expert sends probabilistic forecasts to a …

Consider a multi-class labelling problem, where the labels can take values in $[k] $, and a
predictor predicts a distribution over the labels. In this work, we study the following …

This note provides a survey for the Economics and Computation community of some recent
trends in the field of information elicitation. At its core, the field concerns the design of …

We initiate the study of the truthfulness of calibration measures in sequential prediction. A
calibration measure is said to be truthful if the forecaster (approximately) minimizes the …

A sequence of predictions is calibrated if and only if it induces no swap regret to all down-
stream decision tasks. We study the Maximum Swap Regret (MSR) of predictions for binary …

Machine learning is about forecasting. Forecasts, however, obtain their usefulness only
through their evaluation. Machine learning has traditionally focused on types of losses and …