paper-with-me

Papers

Sample-Efficient Omniprediction for Proper Losses

2025-10-14 · Isaac Gibbs, Ryan J. Tibshirani arxiv

We consider the problem of constructing probabilistic predictions that lead to accurate decisions when employed by downstream users to inform actions. For a single decision maker, designing an optimal predictor is equivalent to minimizing a proper loss function corresponding to the negative utility of that individual. For multiple decision makers, our problem can be viewed as a variant of omniprediction in which the goal is to design a single predictor that simultaneously minimizes multiple losses. Existing algorithms for achieving omniprediction broadly fall into two categories: 1) boosting methods that optimize other auxiliary targets such as multicalibration and obtain omniprediction as a corollary, and 2) adversarial two-player game based approaches that estimate and respond to the ``worst-case" loss in an online fashion. We give lower bounds demonstrating that multicalibration is a strictly more difficult problem than omniprediction and thus the former approach must incur suboptimal sample complexity. For the latter approach, we discuss how these ideas can be used to obtain a sample-efficient algorithm through an online-to-batch conversion. This conversion has the downside of returning a complex, randomized predictor. We improve on this method by designing a more direct, unrandomized algorithm that exploits structural elements of the set of proper losses.

📄 PDF Abstract BibTeX arXiv:2510.12769

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Near-Optimal Algorithms for Omniprediction

2025-01-28 · Princewill Okoroafor, Robert Kleinberg, Michael P. Kim

Omnipredictors are simple prediction functions that encode loss-minimizing predictions with respect to a hypothesis class $\mathcal{H}$, simultaneously for every loss function within a class of losses $\mathcal{L}$. In t…

All

Simultaneous Blackwell Approachability and Applications to Multiclass Omniprediction

2026-02-19 · Lunjia Hu, Kevin Tian, Chutong Yang arxiv

Omniprediction is a learning problem that requires suboptimality bounds for each of a family of losses $\mathcal{L}$ against a family of comparator predictors $\mathcal{C}$. We initiate the study of omniprediction in a m…

Panprediction: Optimal Predictions for Any Downstream Task and Loss

2025-10-31 · Sivaraman Balakrishnan, Nika Haghtalab, Daniel Hsu, Brian Lee 외 arxiv

Supervised learning is classically formulated as training a model to minimize a fixed loss function over a fixed distribution, or task. However, an emerging paradigm instead views model training as extracting enough info…

The Importance of Being Smoothly Calibrated

2026-03-16 · Parikshit Gopalan, Konstantinos Stavropoulos, Kunal Talwar, Pranay Tankala arxiv

Recent work has highlighted the centrality of smooth calibration [Kakade and Foster, 2008] as a robust measure of calibration error. We generalize, unify, and extend previous results on smooth calibration, both as a robu…

Sample Efficient Omniprediction and Downstream Swap Regret for Non-Linear Losses

2025-02-18 · Jiuyao Lu, Aaron Roth, Mirah Shi

We define "decision swap regret" which generalizes both prediction for downstream swap regret and omniprediction, and give algorithms for obtaining it for arbitrary multi-dimensional Lipschitz loss functions in online ad…