# Panprediction: Optimal Predictions for Any Downstream Task and Loss

arXiv: https://arxiv.org/abs/2510.27638 · HTML: https://mlsanity.com/paper/2510.27638/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 23 references that are in the map.
- First posted on arXiv 31 Oct 2025.

## Builds on (most cited first, 14 of 14)

- [Algorithmic Stability for Adaptive Data Analysis](https://mlsanity.com/paper/1511.02513/) (2015)
- [Outcome Indistinguishability](https://mlsanity.com/paper/2011.13426/) (2020)
- [Omnipredictors](https://mlsanity.com/paper/2109.05389/) (2021)
- [Loss Minimization through the Lens of Outcome Indistinguishability](https://mlsanity.com/paper/2210.08649/) (2022)
- [U-Calibration: Forecasting for an Unknown Agent](https://mlsanity.com/paper/2307.00168/) (2023)
- [Multi-group Agnostic PAC Learnability](https://mlsanity.com/paper/2105.09989/) (2021)
- [Advancing subgroup fairness via sleeping experts](https://mlsanity.com/paper/1909.08375/) (2019)
- [A Unifying Perspective on Multi-Calibration: Game Dynamics for Multi-Objective Learning](https://mlsanity.com/paper/2302.10863/) (2023)
- [Simple and near-optimal algorithms for hidden stratification and multi-group learning](https://mlsanity.com/paper/2112.12181/) (2021)
- [Truthfulness of Decision-Theoretic Calibration Measures](https://mlsanity.com/paper/2503.02384/) (2025)
- [Group-wise oracle-efficient algorithms for online multi-group learning](https://mlsanity.com/paper/2406.05287/) (2024)
- [Multi-group Learning for Hierarchical Groups](https://mlsanity.com/paper/2402.00258/) (2024)
- [Learning With Multi-Group Guarantees For Clusterable Subpopulations](https://mlsanity.com/paper/2410.14588/) (2024)
- [Agnostic Multi-Robust Learning Using ERM](https://mlsanity.com/paper/2303.08944/) (2023)

## Built on by (most cited first, 4 of 4)

- [Optimal Deterministic Multicalibration and Omniprediction](https://mlsanity.com/paper/2606.20557/) (2026)
- [The price of multi-group transductive learning](https://mlsanity.com/paper/2606.04423/) (2026)
- [ShakyPrepend: A Multi-Group Learner with Improved Sample Complexity](https://mlsanity.com/paper/2603.07319/) (2026)
- [Blackwell Approachability and Gradient Equilibrium are Equivalent](https://mlsanity.com/paper/2606.27315/) (2026)

## Abstract (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 information from data so that the model can be used to minimize many losses on many downstream tasks. We formalize a mathematical framework for this paradigm, which we call panprediction, and study its statistical complexity. Formally, panprediction generalizes omniprediction and sits upstream from multi-group learning, which respectively focus on predictions that generalize to many downstream losses or many downstream tasks, but not both. Concretely, we design algorithms that learn deterministic and randomized panpredictors with tildeO(1/varepsilon3) and tildeO(1/varepsilon2) samples, respectively. Our results demonstrate that under mild assumptions, simultaneously minimizing infinitely many losses on infinitely many tasks can be as statistically easy as minimizing one loss on one task. Along the way, we improve the best known sample complexity guarantee of deterministic omniprediction by a factor of 1/varepsilon, and match all other known sample complexity guarantees of omniprediction and multi-group learning. Our key technical ingredient is a nearly lossless reduction from panprediction to a statistically efficient notion of calibration, called step calibration.