Corpus ID: 226236734

A Learning Theoretic Perspective on Local Explainability

@article{Li2020ALT,
  title={A Learning Theoretic Perspective on Local Explainability},
  author={J. Li and Vaishnavh Nagarajan and G. Plumb and Ameet S. Talwalkar},
  journal={ArXiv},
  year={2020},
  volume={abs/2011.01205}
}
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… Expand
1 Citations

Figures from this paper

Towards Connecting Use Cases and Methods in Interpretable Machine Learning
  • PDF

References

SHOWING 1-10 OF 21 REFERENCES
Uniform convergence may be unable to explain generalization in deep learning
  • 83
  • PDF
Model Agnostic Supervised Local Explanations
  • 48
  • PDF
In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learning
  • 285
  • PDF
Understanding deep learning requires rethinking generalization
  • 2,596
  • PDF
Anchors: High-Precision Model-Agnostic Explanations
  • 562
  • PDF
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
  • 4,419
  • Highly Influential
  • PDF
Stronger generalization bounds for deep nets via a compression approach
  • 325
  • PDF
...
1
2
3
...