# Mixtures of Transparent Local Models

arXiv: https://arxiv.org/abs/2601.10541 · HTML: https://mlsanity.com/paper/2601.10541/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 46 references that are in the map.
- First posted on arXiv 15 Jan 2026.

## Builds on (most cited first, 11 of 11)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [PAC-Bayesian Theory Meets Bayesian Inference](https://mlsanity.com/paper/1605.08636/) (2016)
- [Fairwashing: the risk of rationalization](https://mlsanity.com/paper/1901.09749/) (2019)
- [Interpretable & Explorable Approximations of Black Box Models](https://mlsanity.com/paper/1707.01154/) (2017)
- [Characterizing the risk of fairwashing](https://mlsanity.com/paper/2106.07504/) (2021)
- [Truly Unordered Probabilistic Rule Sets for Multi-class Classification](https://mlsanity.com/paper/2206.08804/) (2022)
- [Learning Hybrid Interpretable Models: Theory, Taxonomy, and Methods](https://mlsanity.com/paper/2303.04437/) (2023)
- [Scalable Rule Lists Learning with Sampling](https://mlsanity.com/paper/2406.12803/) (2024)
- [Kullback-Leibler Divergence for the Normal-Gamma Distribution](https://mlsanity.com/paper/1611.01437/) (2016)
- [Interpretable Companions for Black-Box Models](https://mlsanity.com/paper/2002.03494/) (2020)

## Abstract (arXiv)

The predominance of machine learning models in many spheres of human activity has led to a growing demand for their transparency. The transparency of models makes it possible to discern some factors, such as security or non-discrimination. In this paper, we propose a mixture of transparent local models as an alternative solution for designing interpretable (or transparent) models. Our approach is designed for the situations where a simple and transparent function is suitable for modeling the label of instances in some localities/regions of the input space, but may change abruptly as we move from one locality to another. Consequently, the proposed algorithm is to learn both the transparent labeling function and the locality of the input space where the labeling function achieves a small risk in its assigned locality. By using a new multi-predictor (and multi-locality) loss function, we established rigorous PAC-Bayesian risk bounds for the case of binary linear classification problem and that of linear regression. In both cases, synthetic data sets were used to illustrate how the learning algorithms work. The results obtained from real data sets highlight the competitiveness of our approach compared to other existing methods as well as certain opaque models. Keywords: PAC-Bayes, risk bounds, local models, transparent models, mixtures of local transparent models.