# Conditional Autoregressors are Interpretable Classifiers

arXiv: https://arxiv.org/abs/2203.17002 · HTML: https://mlsanity.com/paper/2203.17002/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 8 references that are in the map.
- First posted on arXiv 31 Mar 2022.

## Builds on (most cited first, 7 of 7)

- [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)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications](https://mlsanity.com/paper/1701.05517/) (2017)
- [Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Survey](https://mlsanity.com/paper/2006.11371/) (2020)
- [Grad-CAM: Why did you say that?](https://mlsanity.com/paper/1611.07450/) (2016)
- [Classification Accuracy Score for Conditional Generative Models](https://mlsanity.com/paper/1905.10887/) (2019)

## Abstract (arXiv)

We explore the use of class-conditional autoregressive (CA) models to perform image classification on MNIST-10. Autoregressive models assign probability to an entire input by combining probabilities from each individual feature; hence classification decisions made by a CA can be readily decomposed into contributions from each each input feature. That is to say, CA are inherently locally interpretable. Our experiments show that naively training a CA achieves much worse accuracy compared to a standard classifier, however this is due to over-fitting and not a lack of expressive power. Using knowledge distillation from a standard classifier, a student CA can be trained to match the performance of the teacher while still being interpretable.