# On the Consistency of Ordinal Regression Methods

arXiv: https://arxiv.org/abs/1408.2327 · HTML: https://mlsanity.com/paper/1408.2327/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Aug 2014.

## Built on by (most cited first, 24 of 24)

- [Cross-Entropy Loss Functions: Theoretical Analysis and Applications](https://mlsanity.com/paper/2304.07288/) (2023)
- [H-Consistency Guarantees for Regression](https://mlsanity.com/paper/2403.19480/) (2024)
- [Enhanced H-Consistency Bounds](https://mlsanity.com/paper/2407.13722/) (2024)
- [Surrogate Regret Bounds for Polyhedral Losses](https://mlsanity.com/paper/2110.14031/) (2021)
- [Multi stain graph fusion for multimodal integration in pathology](https://mlsanity.com/paper/2204.12541/) (2022)
- [Estimating Parkinsonism Severity in Natural Gait Videos of Older Adults with Dementia](https://mlsanity.com/paper/2105.03464/) (2021)
- [The Rate of Convergence of Variation-Constrained Deep Neural Networks](https://mlsanity.com/paper/2106.12068/) (2021)
- [Parallel Algorithm for Optimal Threshold Labeling of Ordinal Regression Methods](https://mlsanity.com/paper/2405.12756/) (2024)
- [Continuously Generalized Ordinal Regression for Linear and Deep Models](https://mlsanity.com/paper/2202.07005/) (2022)
- [Remarks on Loss Function of Threshold Method for Ordinal Regression Problem](https://mlsanity.com/paper/2405.13288/) (2024)
- [TOC-UCO: a comprehensive repository of tabular ordinal classification datasets](https://mlsanity.com/paper/2507.17348/) (2025)
- [Deep Learning Techniques for Visual Counting](https://mlsanity.com/paper/2206.03033/) (2022)
- [Learning from Positive and Unlabeled Data with Augmented Classes](https://mlsanity.com/paper/2207.13274/) (2022)
- [Convolutional and Deep Learning based techniques for Time Series Ordinal Classification](https://mlsanity.com/paper/2306.10084/) (2023)
- [Regularization-Based Methods for Ordinal Quantification](https://mlsanity.com/paper/2310.09210/) (2023)
- [Consistency Conditions for Differentiable Surrogate Losses](https://mlsanity.com/paper/2505.13760/) (2025)
- [Provably Minimum-Length Conformal Prediction Sets for Ordinal Classification](https://mlsanity.com/paper/2511.16845/) (2025)
- [Interpretability from the Ground Up: Stakeholder-Centric Design of Automated Scoring in Educational Assessments](https://mlsanity.com/paper/2511.17069/) (2025)
- [Natural Language Processing Methods to Identify Oncology Patients at High Risk for Acute Care with Clinical Notes](https://mlsanity.com/paper/2209.13860/) (2022)
- [Some Robustness Properties of Label Cleaning](https://mlsanity.com/paper/2509.11379/) (2025)
- [PREFAB: PREFerence-based Affective Modeling for Low-Budget Self-Annotation](https://mlsanity.com/paper/2601.13904/) (2026)
- [Video-Text Temporal Localization via Multi-Scale Convolution and Dynamic Routing](https://mlsanity.com/paper/2607.05093/) (2026)
- [Application of machine learning to monster level prediction in tabletop RPG game design](https://mlsanity.com/paper/2607.09196/) (2026)
- [QASP: Query-Adaptive Robust Vector Search Policy](https://mlsanity.com/paper/2607.29606/) (2026)

## Abstract (arXiv)

Many of the ordinal regression models that have been proposed in the literature can be seen as methods that minimize a convex surrogate of the zero-one, absolute, or squared loss functions. A key property that allows to study the statistical implications of such approximations is that of Fisher consistency. Fisher consistency is a desirable property for surrogate loss functions and implies that in the population setting, i.e., if the probability distribution that generates the data were available, then optimization of the surrogate would yield the best possible model. In this paper we will characterize the Fisher consistency of a rich family of surrogate loss functions used in the context of ordinal regression, including support vector ordinal regression, ORBoosting and least absolute deviation. We will see that, for a family of surrogate loss functions that subsumes support vector ordinal regression and ORBoosting, consistency can be fully characterized by the derivative of a real-valued function at zero, as happens for convex margin-based surrogates in binary classification. We also derive excess risk bounds for a surrogate of the absolute error that generalize existing risk bounds for binary classification. Finally, our analysis suggests a novel surrogate of the squared error loss. We compare this novel surrogate with competing approaches on 9 different datasets. Our method shows to be highly competitive in practice, outperforming the least squares loss on 7 out of 9 datasets.