# Divide et Calibra: Multiclass Local Calibration via Vector Quantization

arXiv: https://arxiv.org/abs/2605.21060 · HTML: https://mlsanity.com/paper/2605.21060/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 45 references that are in the map.
- First posted on arXiv 20 May 2026.

## Builds on (most cited first, 27 of 27)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Revisiting Deep Learning Models for Tabular Data](https://mlsanity.com/paper/2106.11959/) (2021)
- [MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classification](https://mlsanity.com/paper/2110.14795/) (2021)
- [Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations](https://mlsanity.com/paper/2204.02937/) (2022)
- [Beyond temperature scaling: Obtaining well-calibrated multiclass probabilities with Dirichlet calibration](https://mlsanity.com/paper/1910.12656/) (2019)
- [MedMNIST Classification Decathlon: A Lightweight AutoML Benchmark for Medical Image Analysis](https://mlsanity.com/paper/2010.14925/) (2020)
- [Evaluating model calibration in classification](https://mlsanity.com/paper/1902.06977/) (2019)
- [Shifts: A Dataset of Real Distributional Shift Across Multiple Large-Scale Tasks](https://mlsanity.com/paper/2107.07455/) (2021)
- [Local Temperature Scaling for Probability Calibration](https://mlsanity.com/paper/2008.05105/) (2020)
- [Calibration in Deep Learning: A Survey of the State-of-the-Art](https://mlsanity.com/paper/2308.01222/) (2023)
- [Moment Multicalibration for Uncertainty Estimation](https://mlsanity.com/paper/2008.08037/) (2020)
- [Metrics of calibration for probabilistic predictions](https://mlsanity.com/paper/2205.09680/) (2022)
- [Local Calibration: Metrics and Recalibration](https://mlsanity.com/paper/2102.10809/) (2021)
- [Proximity-Informed Calibration for Deep Neural Networks](https://mlsanity.com/paper/2306.04590/) (2023)
- [Multicalibrated Regression for Downstream Fairness](https://mlsanity.com/paper/2209.07312/) (2022)
- [Taking a Step Back with KCal: Multi-Class Kernel-Based Calibration for Deep Neural Networks](https://mlsanity.com/paper/2202.07679/) (2022)
- [Structured Matrix Scaling for Multi-Class Calibration](https://mlsanity.com/paper/2511.03685/) (2025)
- [Voronoi Density Estimator for High-Dimensional Data: Computation, Compactification and Convergence](https://mlsanity.com/paper/2206.08051/) (2022)
- [Discretization-free Multicalibration through Loss Minimization over Tree Ensembles](https://mlsanity.com/paper/2505.17435/) (2025)
- [Understanding Calibration of Deep Neural Networks for Medical Image Classification](https://mlsanity.com/paper/2309.13132/) (2023)
- [MCGrad: Multicalibration at Web Scale](https://mlsanity.com/paper/2509.19884/) (2025)
- [DiVeQ: Differentiable Vector Quantization Using the Reparameterization Trick](https://mlsanity.com/paper/2509.26469/) (2025)
- [Multiclass Local Calibration with the Jensen-Shannon Distance](https://mlsanity.com/paper/2510.26566/) (2025)
- [Multicalibration Yields Better Matchings](https://mlsanity.com/paper/2511.11413/) (2025)

## Built on by (most cited first, 1 of 1)

- [A CaLLM Judge is a Better Judge: Mitigating Bias in LLM-as-a-judge](https://mlsanity.com/paper/2610.18108/) (2026)

## Abstract (arXiv)

Accurate and well-calibrated Machine Learning (ML) models are mandatory in high-stakes settings, yet effective multiclass calibration remains challenging: global approaches assume calibration errors are homogeneous across the latent space, while local methods often rely on latent-space dimensionality reduction, which leads to information loss. To address these issues, we propose a compositional approach to multiclass calibration, where region-specific calibration maps are constructed from shared codeword-dependent factors. We instantiate this idea via Vector Quantization (VQ), which induces a structured partition of the representation space, and an indexed parameterization of Dirichlet concentrations that enables parameter sharing across regions. Our approach learns heterogeneous calibration maps that generalize well even to sparse regions of the latent space. Experiments on benchmark datasets show significant improvements in local calibration while maintaining competitive global calibration and predictive performance.