Saved in:
Bibliographic Details
Main Authors: Tang, Jingwu, Wu, Jiayun, Wu, Zhiwei Steven, Zhang, Jiahao
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.15615
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908331695669248
author Tang, Jingwu
Wu, Jiayun
Wu, Zhiwei Steven
Zhang, Jiahao
author_facet Tang, Jingwu
Wu, Jiayun
Wu, Zhiwei Steven
Zhang, Jiahao
contents When model predictions inform downstream decision making, a natural question is under what conditions can the decision-makers simply respond to the predictions as if they were the true outcomes. Calibration suffices to guarantee that simple best-response to predictions is optimal. However, calibration for high-dimensional prediction outcome spaces requires exponential computational and statistical complexity. The recent relaxation known as decision calibration ensures the optimality of the simple best-response rule while requiring only polynomial sample complexity in the dimension of outcomes. However, known results on calibration and decision calibration crucially rely on linear loss functions for establishing best-response optimality. A natural approach to handle nonlinear losses is to map outcomes $y$ into a feature space $ϕ(y)$ of dimension $m$, then approximate losses with linear functions of $ϕ(y)$. Unfortunately, even simple classes of nonlinear functions can demand exponentially large or infinite feature dimensions $m$. A key open problem is whether it is possible to achieve decision calibration with sample complexity independent of~$m$. We begin with a negative result: even verifying decision calibration under standard deterministic best response inherently requires sample complexity polynomial in~$m$. Motivated by this lower bound, we investigate a smooth version of decision calibration in which decision-makers follow a smooth best-response. This smooth relaxation enables dimension-free decision calibration algorithms. We introduce algorithms that, given $\mathrm{poly}(|A|,1/ε)$ samples and any initial predictor~$p$, can efficiently post-process it to satisfy decision calibration without worsening accuracy. Our algorithms apply broadly to function classes that can be well-approximated by bounded-norm functions in (possibly infinite-dimensional) separable RKHS.
format Preprint
id arxiv_https___arxiv_org_abs_2504_15615
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Dimension-Free Decision Calibration for Nonlinear Loss Functions
Tang, Jingwu
Wu, Jiayun
Wu, Zhiwei Steven
Zhang, Jiahao
Machine Learning
When model predictions inform downstream decision making, a natural question is under what conditions can the decision-makers simply respond to the predictions as if they were the true outcomes. Calibration suffices to guarantee that simple best-response to predictions is optimal. However, calibration for high-dimensional prediction outcome spaces requires exponential computational and statistical complexity. The recent relaxation known as decision calibration ensures the optimality of the simple best-response rule while requiring only polynomial sample complexity in the dimension of outcomes. However, known results on calibration and decision calibration crucially rely on linear loss functions for establishing best-response optimality. A natural approach to handle nonlinear losses is to map outcomes $y$ into a feature space $ϕ(y)$ of dimension $m$, then approximate losses with linear functions of $ϕ(y)$. Unfortunately, even simple classes of nonlinear functions can demand exponentially large or infinite feature dimensions $m$. A key open problem is whether it is possible to achieve decision calibration with sample complexity independent of~$m$. We begin with a negative result: even verifying decision calibration under standard deterministic best response inherently requires sample complexity polynomial in~$m$. Motivated by this lower bound, we investigate a smooth version of decision calibration in which decision-makers follow a smooth best-response. This smooth relaxation enables dimension-free decision calibration algorithms. We introduce algorithms that, given $\mathrm{poly}(|A|,1/ε)$ samples and any initial predictor~$p$, can efficiently post-process it to satisfy decision calibration without worsening accuracy. Our algorithms apply broadly to function classes that can be well-approximated by bounded-norm functions in (possibly infinite-dimensional) separable RKHS.
title Dimension-Free Decision Calibration for Nonlinear Loss Functions
topic Machine Learning
url https://arxiv.org/abs/2504.15615