# A Learning Theoretic Perspective on Local Explainability

arXiv: https://arxiv.org/abs/2011.01205 · HTML: https://mlsanity.com/paper/2011.01205/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Nov 2020.

## Built on by (most cited first, 11 of 11)

- [TalkToModel: Explaining Machine Learning Models with Interactive Natural Language Conversations](https://mlsanity.com/paper/2207.04154/) (2022)
- [Interpretable Machine Learning: Moving From Mythos to Diagnostics](https://mlsanity.com/paper/2103.06254/) (2021)
- [Learning with Explanation Constraints](https://mlsanity.com/paper/2303.14496/) (2023)
- [On the Impact of Knowledge Distillation for Model Interpretability](https://mlsanity.com/paper/2305.15734/) (2023)
- [A Theory of Interpretable Approximations](https://mlsanity.com/paper/2406.10529/) (2024)
- [Analyzing Explainer Robustness via Probabilistic Lipschitzness of Prediction Functions](https://mlsanity.com/paper/2206.12481/) (2022)
- [Efficient and Accurate Explanation Estimation with Distribution Compression](https://mlsanity.com/paper/2406.18334/) (2024)
- [Finding Safe Zones of policies Markov Decision Processes](https://mlsanity.com/paper/2202.11593/) (2022)
- [DAM: Diffusion Activation Maximization for 3D Global Explanations](https://mlsanity.com/paper/2401.14938/) (2024)
- [Comparables XAI: Faithful Example-based AI Explanations with Counterfactual Trace Adjustments](https://mlsanity.com/paper/2602.13784/) (2026)
- [Probabilistic Linear Explanations](https://mlsanity.com/paper/2609.19077/) (2026)

## Abstract (arXiv)

In this paper, we explore connections between interpretable machine learning and learning theory through the lens of local approximation explanations. First, we tackle the traditional problem of performance generalization and bound the test-time accuracy of a model using a notion of how locally explainable it is. Second, we explore the novel problem of explanation generalization which is an important concern for a growing class of finite sample-based local approximation explanations. Finally, we validate our theoretical results empirically and show that they reflect what can be seen in practice.