# Efficient Calibration for Decision Making

arXiv: https://arxiv.org/abs/2511.13699 · HTML: https://mlsanity.com/paper/2511.13699/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 53 references that are in the map.
- First posted on arXiv 17 Nov 2025.

## Builds on (most cited first, 25 of 25)

- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Mitigating Bias in Calibration Error Estimation](https://mlsanity.com/paper/2012.08668/) (2020)
- [Calibrating Predictions to Decisions: A Novel Approach to Multi-Class Calibration](https://mlsanity.com/paper/2107.05719/) (2021)
- [Outcome Indistinguishability](https://mlsanity.com/paper/2011.13426/) (2020)
- [Omnipredictors](https://mlsanity.com/paper/2109.05389/) (2021)
- [Smooth ECE: Principled Reliability Diagrams via Kernel Smoothing](https://mlsanity.com/paper/2309.12236/) (2023)
- [Loss Minimization through the Lens of Outcome Indistinguishability](https://mlsanity.com/paper/2210.08649/) (2022)
- [A Unifying Theory of Distance from Calibration](https://mlsanity.com/paper/2211.16886/) (2022)
- [U-Calibration: Forecasting for an Unknown Agent](https://mlsanity.com/paper/2307.00168/) (2023)
- [Distribution-free calibration guarantees for histogram binning without sample splitting](https://mlsanity.com/paper/2105.04656/) (2021)
- [Low-Degree Multicalibration](https://mlsanity.com/paper/2203.01255/) (2022)
- [When Does Optimizing a Proper Loss Yield Calibration?](https://mlsanity.com/paper/2305.18764/) (2023)
- [Near-Optimal Algorithms for Omniprediction](https://mlsanity.com/paper/2501.17205/) (2025)
- [Rethinking Early Stopping: Refine, Then Calibrate](https://mlsanity.com/paper/2501.19195/) (2025)
- [Complexity-Theoretic Implications of Multicalibration](https://mlsanity.com/paper/2312.17223/) (2023)
- [On Computationally Efficient Multi-Class Calibration](https://mlsanity.com/paper/2402.07821/) (2024)
- [Calibration Error for Decision Making](https://mlsanity.com/paper/2404.13503/) (2024)
- [Optimal Scoring Rules for Multi-dimensional Effort](https://mlsanity.com/paper/2211.03302/) (2022)
- [Can a calibration metric be both testable and actionable?](https://mlsanity.com/paper/2502.19851/) (2025)
- [Minimum-Risk Recalibration of Classifiers](https://mlsanity.com/paper/2305.10886/) (2023)
- [Testing Calibration in Nearly-Linear Time](https://mlsanity.com/paper/2402.13187/) (2024)
- [Smooth Calibration and Decision Making](https://mlsanity.com/paper/2504.15582/) (2025)
- [The PAV algorithm optimizes binary proper scoring rules](https://mlsanity.com/paper/1304.2331/) (2013)
- [Generalized and Unified Equivalences between Hardness and Pseudoentropy](https://mlsanity.com/paper/2507.05972/) (2025)
- [Calibration through the Lens of Indistinguishability](https://mlsanity.com/paper/2509.02279/) (2025)

## Built on by (most cited first, 3 of 3)

- [The Importance of Being Smoothly Calibrated](https://mlsanity.com/paper/2603.16015/) (2026)
- [Testable and Actionable Calibration for Full Swap Regret](https://mlsanity.com/paper/2605.17749/) (2026)
- [Human-AI Teaming Through the Lens of Calibration](https://mlsanity.com/paper/2606.10906/) (2026)

## Abstract (arXiv)

A decision-theoretic characterization of perfect calibration is that an agent seeking to minimize a proper loss in expectation cannot improve their outcome by post-processing a perfectly calibrated predictor. Hu and Wu (FOCS'24) use this to define an approximate calibration measure called calibration decision loss (mathsfCDL), which measures the maximal improvement achievable by any post-processing over any proper loss. Unfortunately, mathsfCDL turns out to be intractable to even weakly approximate in the offline setting, given black-box access to the predictions and labels. We suggest circumventing this by restricting attention to structured families of post-processing functions K. We define the calibration decision loss relative to K, denoted mathsfCDLK where we consider all proper losses but restrict post-processings to a structured family K. We develop a comprehensive theory of when mathsfCDLK is information-theoretically and computationally tractable, and use it to prove both upper and lower bounds for natural classes K. In addition to introducing new definitions and algorithmic techniques to the theory of calibration for decision making, our results give rigorous guarantees for some widely used recalibration procedures in machine learning.