Faster online calibration without randomization: interval forecasts and the power of two choices

04/27/2022
by   Chirag Gupta, et al.
0

We study the problem of making calibrated probabilistic forecasts for a binary sequence generated by an adversarial nature. Following the seminal paper of Foster and Vohra (1998), nature is often modeled as an adaptive adversary who sees all activity of the forecaster except the randomization that the forecaster may deploy. A number of papers have proposed randomized forecasting strategies that achieve an ϵ-calibration error rate of O(1/√(T)), which we prove is tight in general. On the other hand, it is well known that it is not possible to be calibrated without randomization, or if nature also sees the forecaster's randomization; in both cases the calibration error could be Ω(1). Inspired by the equally seminal works on the "power of two choices" and imprecise probability theory, we study a small variant of the standard online calibration problem. The adversary gives the forecaster the option of making two nearby probabilistic forecasts, or equivalently an interval forecast of small width, and the endpoint closest to the revealed outcome is used to judge calibration. This power of two choices, or imprecise forecast, accords the forecaster with significant power – we show that a faster ϵ-calibration rate of O(1/T) can be achieved even without deploying any randomization.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/13/2022

Forecast Hedging and Calibration

Calibration means that forecasts and average realized frequencies are cl...
research
06/18/2020

Individual Calibration with Randomized Forecasting

Machine learning applications often require calibrated predictions, e.g....
research
09/13/2022

Calibrated Forecasts: The Minimax Proof

A formal write-up of the simple proof (1995) of the existence of calibra...
research
06/30/2023

U-Calibration: Forecasting for an Unknown Agent

We consider the problem of evaluating forecasts of binary events whose p...
research
09/11/2022

"Calibeating": Beating Forecasters at Their Own Game

In order to identify expertise, forecasters should not be tested by thei...
research
01/25/2023

Evaluating Probabilistic Classifiers: The Triptych

Probability forecasts for binary outcomes, often referred to as probabil...
research
10/22/2014

Log-Optimal Portfolio Selection Using the Blackwell Approachability Theorem

We present a method for constructing the log-optimal portfolio using the...

Please sign up or login with your details

Forgot password? Click here to reset