1 code implementation • 13 Jan 2023 • Surin Ahn, Justin Grana, Yafet Tamene, Kristian Holsheimer
We present a model-agnostic algorithm for generating post-hoc explanations and uncertainty intervals for a machine learning model when only a static sample of inputs and outputs from the model is available, rather than direct access to the model itself.
no code implementations • 21 May 2020 • Surin Ahn, Ayfer Ozgur, Mert Pilanci
In the domains of dataset construction and crowdsourcing, a notable challenge is to aggregate labels from a heterogeneous set of labelers, each of whom is potentially an expert in some subset of tasks (and less reliable in others).