Carlos Guestrin

Carlos Guestrin, machine-learning researcher and the senior author of LIME. The Amazon Professor of Machine Learning at the University of Washington in 2016; he co-founded Turi (formerly GraphLab), acquired by Apple in 2016, and led machine-learning teams at Apple before becoming a professor of computer science at Stanford.

Stake§

Professional and reputational, with industry ties — his companies and roles sit adjacent to a commercial market for explainability and ML tooling, though the KDD paper itself carries no product.

Guestrin's role in this topic is as senior author of LIME, the post-hoc explanation method. The agenda he helped launch — explaining models from the outside rather than building them transparent — is the pole Rudin argues against for high-stakes use, and its legal analogue appears in Wachter, Mittelstadt and Russell's counterfactual explanations.

Works in this corpus§

"Why Should I Trust You?": Explaining the Predictions of Any Classifier

¶ excerpts

Despite widespread adoption, machine learning models remain mostly black boxes. Understanding the reasons behind predictions is, however, quite important in assessing trust, which is fundamental if one plans to take action based on a prediction, or when choosing whether to deploy a new model.

— "Why Should I Trust You?": Explaining the Predictions of Any Classifier (2016)

The framing that set the post-hoc [[concept:explainability|explanation]] agenda: the model stays a black box, but a local explanation of each prediction is offered as the basis for trust.

on Explainability

We propose LIME, a novel explanation technique that explains the predictions of any classifier in an interpretable and faithful manner, by learning an interpretable model locally around the prediction.

— "Why Should I Trust You?": Explaining the Predictions of Any Classifier (2016)

LIME fits a simple, transparent model in the neighbourhood of a single prediction to approximate the black box there. The word "faithful" is the load the method is asked to carry — and the same word names the property that [[source:turpin-2023-language-models-dont-always-say-what-they-think|Turpin]] later finds chain-of-thought explanations lack.

on Explainability, Explanation faithfulness