Breaking the T^(2/3) Barrier for Sequential Calibration
Name
3717823.3718178.pdf
Size
756.36 KB
Format
Adobe PDF
Checksum (MD5)
4c67e52e7527c6bc81b7b2e541b7185d
Author(s) • • • • •
Dagan, Yuval
Daskalakis, Constantinos
Fishelson, Maxwell
Golowich, Noah
Kleinberg, Robert
Okoroafor, Princewill
Date Issued
June 15, 2025
Publisher
ACM|Proceedings of the 57th Annual ACM Symposium on Theory of Computing
Citation
Yuval Dagan, Constantinos Daskalakis, Maxwell Fishelson, Noah Golowich, Robert Kleinberg, and Princewill Okoroafor. 2025. Breaking the T^(2/3) Barrier for Sequential Calibration. In Proceedings of the 57th Annual ACM Symposium on Theory of Computing (STOC '25). Association for Computing Machinery, New York, NY, USA, 2007–2018.
Version
Final published version
Abstract
A set of probabilistic forecasts is calibrated if each prediction of the forecaster closely approximates the empirical distribution of outcomes on the subset of timesteps where that prediction was made. We study the fundamental problem of online calibrated forecasting of binary sequences, which was initially studied by Foster and Vohra. They derived an algorithm with O(T2/3) calibration error after T time steps, and showed a lower bound of Ω(T1/2). These bounds remained stagnant for two decades, until Qiao and Valiant improved the lower bound to Ω(T0.528) by introducing a combinatorial game called sign preservation and showing that lower bounds for this game imply lower bounds for calibration.
In this paper, we give the first improvement to the O(T2/3) upper bound on calibration error of Foster and Vohra.
We do this by introducing a variant of Qiao and Valiant’s game that we call sign preservation with reuse (SPR). We prove that the relationship between SPR and calibrated forecasting is bidirectional: not only do lower bounds for SPR translate into lower bounds for calibration, but algorithms for SPR also translate into new algorithms for calibrated forecasting. We then give an improved upper bound for the SPR game, which implies, via our equivalence, a forecasting algorithm with calibration error O(T2/3 − ) for some > 0, improving Foster and Vohra’s upper bound for the first time. Using similar ideas, we then prove a slightly stronger lower bound than that of Qiao and Valiant, namely Ω(T0.54389). Our lower bound is obtained by an oblivious adversary, marking the first ω(T1/2) calibration lower bound for oblivious adversaries.
Description
STOC ’25, Prague, Czechia
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Creative Commons Attribution
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1145/3717823.3718178