Newshot

A Matching Lower Bound for Online Smooth Calibration

Summary

arXiv:2611.16097v2 Announce Type: replace-cross Abstract: We study smooth calibration error in sequential binary prediction, a measure of how far probabilistic forecasts are from being calibrated that is robust to small perturbations of the forecasts. The minimax smooth calibration error is known to lie between $\Omega(T^{1/3})$ and $O(\sqrt T)$(Qiao and Zheng, 2024), where $T$ is the number of rounds. We close this gap for both adaptive and oblivious adversaries. We construct an adaptive adversary whose outcome mean moves with the forecaster's cumulative residual, which makes compensating for past residuals costly and forces every forecaster to incur $\Omega(\sqrt T)$ expected smooth calibration error. Simulating this adversary against the forecaster's average prediction yields an oblivious adversary with the same guarantee. These lower bounds match the known $O(\sqrt T)$ upper bound up to universal constants, and are therefore minimax optimal. Our results also imply matching $\Theta(…

Original text(via arXiv stat.ML)

Computer Science > Machine Learning

Title:A Matching Lower Bound for Online Smooth Calibration

Abstract:We study smooth calibration error in sequential binary prediction, a measure of how far probabilistic forecasts are from being calibrated that is robust to small perturbations of the forecasts. The minimax smooth calibration error is known to lie between $\Omega(T^{1/3})$ and $O(\sqrt T)$(Qiao and Zheng, 2024), where $T$ is the number of rounds. We close this gap for both adaptive and oblivious adversaries. We construct an adaptive adversary whose outcome mean moves with the forecaster's cumulative residual, which makes compensating for past residuals costly and forces every forecaster to incur $\Omega(\sqrt T)$ expected smooth calibration error. Simulating this adversary against the forecaster's average prediction yields an oblivious adversary with the same guarantee. These lower bounds match the known $O(\sqrt T)$ upper bound up to universal constants, and are therefore minimax optimal. Our results also imply matching $\Theta(\sqrt T)$ bounds for calibration distance and lower calibration distance. The proof ideas are partially developed by GPT-6 Astra under the authors' guidance.
Subjects:Machine Learning (cs.LG) ; Machine Learning (stat.ML)
Cite as:arXiv:2611.16097 [cs.LG]
(or arXiv:2611.16097v2 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2611.16097 arXiv-issued DOI via DataCite

Submission history

Access Paper:

  • HTML (experimental)

Additional Features

  • Audio Summary

Current browse context:

References & Citations

  • Google Scholar
  • Semantic Scholar

BibTeX formatted citation

Bookmark

Bibliographic and Citation Tools

Code, Data and Media Associated with this Article

Demos

Recommenders and Search Tools

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

The text above was extracted automatically from the source page and may miss images, tables or code blocks. The original is authoritative.

Published by arXiv stat.ML
This site only summarises and aggregates; copyright stays with the original author. Headlines and summaries follow the source — where they differ, the original wins.
Read the original ↗