High-Dimensional Calibration from Swap Regret

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Fishelson, Maxwell, Golowich, Noah, Mohri, Mehryar, Schneider, Jon
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912398315618304
author Fishelson, Maxwell
Golowich, Noah
Mohri, Mehryar
Schneider, Jon
author_facet Fishelson, Maxwell
Golowich, Noah
Mohri, Mehryar
Schneider, Jon
contents We study the online calibration of multi-dimensional forecasts over an arbitrary convex set $\mathcal{P} \subset \mathbb{R}^d$ relative to an arbitrary norm $\Vert\cdot\Vert$. We connect this with the problem of external regret minimization for online linear optimization, showing that if it is possible to guarantee $O(\sqrt{ρT})$ worst-case regret after $T$ rounds when actions are drawn from $\mathcal{P}$ and losses are drawn from the dual $\Vert \cdot \Vert_*$ unit norm ball, then it is also possible to obtain $ε$-calibrated forecasts after $T = \exp(O(ρ/ε^2))$ rounds. When $\mathcal{P}$ is the $d$-dimensional simplex and $\Vert \cdot \Vert$ is the $\ell_1$-norm, the existence of $O(\sqrt{T\log d})$-regret algorithms for learning with experts implies that it is possible to obtain $ε$-calibrated forecasts after $T = \exp(O(\log{d}/ε^2)) = d^{O(1/ε^2)}$ rounds, recovering a recent result of Peng (2025). Interestingly, our algorithm obtains this guarantee without requiring access to any online linear optimization subroutine or knowledge of the optimal rate $ρ$ -- in fact, our algorithm is identical for every setting of $\mathcal{P}$ and $\Vert \cdot \Vert$. Instead, we show that the optimal regularizer for the above OLO problem can be used to upper bound the above calibration error by a swap regret, which we then minimize by running the recent TreeSwap algorithm with Follow-The-Leader as a subroutine. Finally, we prove that any online calibration algorithm that guarantees $εT$ $\ell_1$-calibration error over the $d$-dimensional simplex requires $T \geq \exp(\mathrm{poly}(1/ε))$ (assuming $d \geq \mathrm{poly}(1/ε)$). This strengthens the corresponding $d^{Ω(\log{1/ε})}$ lower bound of Peng, and shows that an exponential dependence on $1/ε$ is necessary.
format Preprint
id arxiv_https___arxiv_org_abs_2505_21460
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle High-Dimensional Calibration from Swap Regret
Fishelson, Maxwell
Golowich, Noah
Mohri, Mehryar
Schneider, Jon
Machine Learning
Data Structures and Algorithms
Computer Science and Game Theory
We study the online calibration of multi-dimensional forecasts over an arbitrary convex set $\mathcal{P} \subset \mathbb{R}^d$ relative to an arbitrary norm $\Vert\cdot\Vert$. We connect this with the problem of external regret minimization for online linear optimization, showing that if it is possible to guarantee $O(\sqrt{ρT})$ worst-case regret after $T$ rounds when actions are drawn from $\mathcal{P}$ and losses are drawn from the dual $\Vert \cdot \Vert_*$ unit norm ball, then it is also possible to obtain $ε$-calibrated forecasts after $T = \exp(O(ρ/ε^2))$ rounds. When $\mathcal{P}$ is the $d$-dimensional simplex and $\Vert \cdot \Vert$ is the $\ell_1$-norm, the existence of $O(\sqrt{T\log d})$-regret algorithms for learning with experts implies that it is possible to obtain $ε$-calibrated forecasts after $T = \exp(O(\log{d}/ε^2)) = d^{O(1/ε^2)}$ rounds, recovering a recent result of Peng (2025). Interestingly, our algorithm obtains this guarantee without requiring access to any online linear optimization subroutine or knowledge of the optimal rate $ρ$ -- in fact, our algorithm is identical for every setting of $\mathcal{P}$ and $\Vert \cdot \Vert$. Instead, we show that the optimal regularizer for the above OLO problem can be used to upper bound the above calibration error by a swap regret, which we then minimize by running the recent TreeSwap algorithm with Follow-The-Leader as a subroutine. Finally, we prove that any online calibration algorithm that guarantees $εT$ $\ell_1$-calibration error over the $d$-dimensional simplex requires $T \geq \exp(\mathrm{poly}(1/ε))$ (assuming $d \geq \mathrm{poly}(1/ε)$). This strengthens the corresponding $d^{Ω(\log{1/ε})}$ lower bound of Peng, and shows that an exponential dependence on $1/ε$ is necessary.
title High-Dimensional Calibration from Swap Regret
topic Machine Learning
Data Structures and Algorithms
Computer Science and Game Theory
url https://arxiv.org/abs/2505.21460