arXiv：cs.LG· S\'ilvia Casacuberta, Parikshit Gopalan, Varun Kanade, Omer Reingold, Konstantinos Stavropoulos, Pranay Tankala·· 4 小时前AI 评分34
多群体公平性与全能预测：GPT 等模型全能预测是否需要公平性约束？分离与等价结果
Multigroup Fairness and Omniprediction: Separations and Equivalences
AI 导读
研究证明全能预测（omniprediction）并不需要多群体公平性：针对恰当的损失函数，全能预测甚至不蕴含期望准确率，比校准、多准确率或多校准都更弱。但更强的 loss OI 与某种校准多准确率等价。该结果被 NeurIPS 2026 接收。
正文
Abstract:Omniprediction is a learning guarantee which requires a single predictor to be competitive relative to the best hypothesis from a benchmark class for any loss chosen from a family of loss functions. Loss Outcome Indistinguishability (loss OI for short) is a stronger notion that implies omniprediction. It requires the predicted distribution on labels to be indistinguishable from the true distribution to tests that depend on the loss functions and the benchmark class. Multiaccuracy and multicalibration are multigroup fairness notions that generalize classical notions of calibration and accuracy in expectation. Most known learning algorithms for omniprediction (both for the standard notion and for strengthenings like loss OI) rely on some version of these multigroup fairness notions, or on an intermediate notion called calibrated multiaccuracy. We ask if this is necessary: Does omniprediction require some form of multigroup fairness?
We show that the answer is no for (plain) omniprediction, and yes for loss OI. First, a sequence of works shows that multicalibration or calibrated multiaccuracy imply omniprediction. We rule out even a weak converse, by showing that omniprediction for proper losses does not imply even accuracy in expectation, a much weaker notion than any of calibration, multiaccuracy, or multicalibration. Second, prior work showed how to achieve loss OI from a combination of calibration and multiaccuracy. We show a converse: loss OI is equivalent to a form of calibrated multiaccuracy.
| Comments: | Accepted for presentation at NeurIPS 2026 |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.07374 [cs.LG] |
| (or arXiv:2610.07374v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.07374 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Sílvia Casacuberta [view email]
[v1]
Mon, 5 Oct 2026 20:45:07 UTC (48 KB)
来源：arXiv：cs.LG · arxiv.org