# Convex Calibration Dimension for Multiclass Loss Matrices

arXiv: https://arxiv.org/abs/1408.2764 · HTML: https://mlsanity.com/paper/1408.2764/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Aug 2014.

## Built on by (most cited first, 21 of 21)

- [Cross-Entropy Loss Functions: Theoretical Analysis and Applications](https://mlsanity.com/paper/2304.07288/) (2023)
- [In Defense of Softmax Parametrization for Calibrated and Consistent Learning to Defer](https://mlsanity.com/paper/2311.01106/) (2023)
- [Enhanced H-Consistency Bounds](https://mlsanity.com/paper/2407.13722/) (2024)
- [An Embedding Framework for the Design and Analysis of Consistent Polyhedral Surrogates](https://mlsanity.com/paper/2206.14707/) (2022)
- [Training Over-parameterized Models with Non-decomposable Objectives](https://mlsanity.com/paper/2107.04641/) (2021)
- [Consistent Polyhedral Surrogates for Top-k Classification and Variants](https://mlsanity.com/paper/2207.08873/) (2022)
- [The Structured Abstain Problem and the Lov'asz Hinge](https://mlsanity.com/paper/2203.08645/) (2022)
- [On Classification-Calibration of Gamma-Phi Losses](https://mlsanity.com/paper/2302.07321/) (2023)
- [Understanding Uncertainty Sampling via Equivalent Loss](https://mlsanity.com/paper/2307.02719/) (2023)
- [Unifying Lower Bounds on Prediction Dimension of Consistent Convex Surrogates](https://mlsanity.com/paper/2102.08218/) (2021)
- [OpReg-Boost: Learning to Accelerate Online Algorithms with Operator Regression](https://mlsanity.com/paper/2105.13271/) (2021)
- [Learning from Positive and Unlabeled Data with Augmented Classes](https://mlsanity.com/paper/2207.13274/) (2022)
- [Trading off Consistency and Dimensionality of Convex Surrogates for the Mode](https://mlsanity.com/paper/2402.10818/) (2024)
- [Contrasting Cost-Agnostic and Cost-Sensitive Losses under Limited Model Capacity via mathcal H-consistency](https://mlsanity.com/paper/2502.19522/) (2025)
- [On Next-Token Prediction in LLMs: How End Goals Determine the Consistency of Decoding Algorithms](https://mlsanity.com/paper/2505.11183/) (2025)
- [Consistency Conditions for Differentiable Surrogate Losses](https://mlsanity.com/paper/2505.13760/) (2025)
- [Exact Rank and Convex Calibration Dimension Lower Bounds for the Multi-Label F1 Loss](https://mlsanity.com/paper/2608.08399/) (2026)
- [Structured Prediction with Abstention via the Lov'asz Hinge](https://mlsanity.com/paper/2505.06446/) (2025)
- [Smoothed Elicitation Complexity for Approximate Gamma-calibration of Discrete Classification Tasks](https://mlsanity.com/paper/2605.23017/) (2026)
- [Exponential Convex Calibration Dimension for the Multi-Label Jaccard Measure](https://mlsanity.com/paper/2608.13549/) (2026)
- [Common Geodesics Do Not Guarantee Fisher Consistency of the Structured SVM: Minimal Counterexamples and a Tree-Metric Classification](https://mlsanity.com/paper/2608.27203/) (2026)

## Abstract (arXiv)

We study consistency properties of surrogate loss functions for general multiclass learning problems, defined by a general multiclass loss matrix. We extend the notion of classification calibration, which has been studied for binary and multiclass 0-1 classification problems (and for certain other specific learning problems), to the general multiclass setting, and derive necessary and sufficient conditions for a surrogate loss to be calibrated with respect to a loss matrix in this setting. We then introduce the notion of convex calibration dimension of a multiclass loss matrix, which measures the smallest `size' of a prediction space in which it is possible to design a convex surrogate that is calibrated with respect to the loss matrix. We derive both upper and lower bounds on this quantity, and use these results to analyze various loss matrices. In particular, we apply our framework to study various subset ranking losses, and use the convex calibration dimension as a tool to show both the existence and non-existence of various types of convex calibrated surrogates for these losses. Our results strengthen recent results of Duchi et al. (2010) and Calauzenes et al. (2012) on the non-existence of certain types of convex calibrated surrogates in subset ranking. We anticipate the convex calibration dimension may prove to be a useful tool in the study and design of surrogate losses for general multiclass learning problems.