Pang Wei Koh, Percy Liang. Understanding Black-Box Predictions via Influence Functions. ICML 2017.
- Takeaway 1
- Takeaway 2
- Open question or critique
Using influence functions, the authors can trace a prediction back to the training data.
- TODO
- The classical result allows you to determine the influence of upweighting training data point on parameters theta. We can use the
- What are the main contributions?
- Point to relevant long parts of paper that are unable to be summarized
- Image classification
TODO